Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional statements and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words of Facebook or non-English words

    np_acts-logits-general · gemini-2.0-flash

    Facebook, Turkmenistan, Russian, Czech, Serbian, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.66
     متعلقه
    -0.61
     fossero
    -0.58
    ImageContext
    -0.58
     للمعارف
    -0.57
    ilderness
    -0.54
     تضيفلها
    -0.53
    mybatisplus
    -0.53
    łóż
    -0.53
     vya
    -0.52
    POSITIVE LOGITS
    migrationBuilder
    0.62
    SerializeField
    0.60
     gladly
    0.60
     successfully
    0.60
     willingly
    0.59
    RenderAtEndOf
    0.56
     дописавши
    0.56
    complexContent
    0.55
     proudly
    0.55
    featureID
    0.55
    Act Density 0.017%

    No Known Activations