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

    Neuronpedia

    INDEX
    Explanations

    words related to fixing or counteracting something

    oai_token-act-pair · gemini-2.0-flash

    words related to software development and commit actions

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    protoimpl
    -0.63
     فريبيس
    -0.61
     viewType
    -0.58
    таратура
    -0.55
    SharedCtor
    -0.54
    withIdentifier
    -0.52
    QMetaType
    -0.52
    javadoc
    -0.50
     surla
    -0.50
    nady
    -0.50
    POSITIVE LOGITS
    ting
    0.85
    table
    0.79
    tings
    0.79
    tableFuture
    0.74
    ted
    0.74
    ⓧ
    0.73
    🏻
    0.69
    ters
    0.64
    🏼
    0.61
    MessageOf
    0.60
    Act Density 3.165%

    No Known Activations