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

    Neuronpedia

    INDEX
    Explanations

    special characters and specific syntactical elements in the text

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

    prepositions in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.67
    :✨
    -0.50
    ing
    -0.43
    /*!
    -0.43
    shot
    -0.41
     Lijst
    -0.41
    artifactId
    -0.41
    足
    -0.40
    いる
    -0.39
    symmetry
    -0.39
    POSITIVE LOGITS
    bootstrapcdn
    0.58
    Erreferentziak
    0.45
     ProtoMessage
    0.44
     forState
    0.43
     Signalez
    0.42
     TableColumn
    0.41
    elementAt
    0.41
     streets
    0.40
    runOnUiThread
    0.40
    xFFFFFF
    0.40
    Act Density 0.000%

    No Known Activations