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

    Neuronpedia

    INDEX
    Explanations

    numerical and quantitative relationships in data

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

    each specific item quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoField
    -0.57
    EndGlobalSection
    -0.51
    featureID
    -0.47
     IndexPath
    -0.46
     SafeMath
    -0.45
    messageInfo
    -0.44
    ModelSerializer
    -0.43
    EndContext
    -0.42
    évaluateur
    -0.42
     Bann
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.44
     PeEnEo
    0.44
    帖最后由
    0.42
     initComponents
    0.41
    antaranya
    0.38
    ❋
    0.38
     jopa
    0.36
    tahui
    0.36
    :]:
    0.36
    atoare
    0.36
    Act Density 0.243%

    No Known Activations