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

    Neuronpedia

    INDEX
    Explanations

    functions and their return statements

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

    statements returning boolean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vors
    -0.45
    uja
    -0.43
    ⠄
    -0.42
    utorial
    -0.41
     rivals
    -0.40
    afe
    -0.40
     Züge
    -0.39
     μη
    -0.39
    不必
    -0.39
    يست
    -0.38
    POSITIVE LOGITS
     AttributeSet
    0.65
    principalColumn
    0.60
    +#+#
    0.60
    SharedDtor
    0.56
    TypedDataSet
    0.54
    MessageOf
    0.54
    UnusedPrivate
    0.53
    RegressionTest
    0.53
    /***/
    0.52
    featureID
    0.52
    Act Density 0.016%

    No Known Activations