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

    Neuronpedia

    INDEX
    Explanations

    identifiers or function declarations in programming code

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

    selection and click events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -1.13
     betweenstory
    -1.05
    AutoScaleMode
    -0.95
     queſta
    -0.93
    featureID
    -0.89
    enterOuterAlt
    -0.86
    UnusedPrivate
    -0.84
     ligiloj
    -0.84
    AddTagHelper
    -0.84
    TestingModule
    -0.81
    POSITIVE LOGITS
    -
    0.52
    _
    0.47
     was
    0.43
     When
    0.42
    When
    0.42
    .
    0.42
    '
    0.41
     being
    0.40
    ’
    0.39
     Lif
    0.39
    Act Density 0.002%

    No Known Activations