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

    Neuronpedia

    INDEX
    Explanations

    sections related to data structure, metadata, or logging in a technical or programming context

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.84
     surla
    -0.77
     gyhoeddwyd
    -0.69
     beginnetje
    -0.68
    ViewImports
    -0.67
    QMetaType
    -0.63
     arşivlendi
    -0.62
    pushFollow
    -0.62
     GenerationType
    -0.61
     ***!
    -0.60
    POSITIVE LOGITS
     görün
    0.37
    KindOfClass
    0.36
     rozs
    0.34
     realistically
    0.34
    setVisible
    0.34
     einsch
    0.33
     souff
    0.32
    writeString
    0.31
     vụ
    0.30
    uis
    0.30
    Act Density 1.196%

    No Known Activations