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

    Neuronpedia

    INDEX
    Explanations

    phrases related to operational instructions and safety precautions

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

    prostrates whoever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     truer
    -0.45
     Honig
    -0.45
    hoff
    -0.45
     CanadaChoose
    -0.45
     للمعارف
    -0.44
     illuminating
    -0.42
     inked
    -0.42
    掺
    -0.41
     hopefully
    -0.41
     싶
    -0.41
    POSITIVE LOGITS
    ChildScrollView
    0.58
    Aholisi
    0.52
     createState
    0.48
    featureID
    0.46
     ſind
    0.45
     ſes
    0.41
    GEBURTS
    0.41
     NSCoder
    0.40
    postIndex
    0.40
    URLException
    0.40
    Act Density 0.008%

    No Known Activations