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

    Neuronpedia

    INDEX
    Explanations

    numbers and commentary related to content organization and responses

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

    Numbers followed by "Responses" or citations

    np_acts-logits-general · gemini-2.0-flash

    numbers and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.64
     }?>
    -0.58
    ViewFeatures
    -0.58
    Spoljašnje
    -0.57
    epiece
    -0.56
    MetaObject
    -0.55
    AutoField
    -0.55
    RegistryLite
    -0.53
     }}\
    -0.52
    Бахар
    -0.51
    POSITIVE LOGITS
     виправивши
    0.73
    InjectAttribute
    0.72
     Перейти
    0.69
     Pingback
    0.65
    TagMode
    0.64
    Koordinaten
    0.62
     esternos
    0.60
     ***!
    0.59
     Saltar
    0.58
    jątk
    0.57
    Act Density 0.039%

    No Known Activations