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

    Neuronpedia

    INDEX
    Explanations

    the phrase 'turn off' or variants of that phrase

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.88
    IsMutable
    -0.87
     للاسماء
    -0.83
     дописавши
    -0.77
    sidemargin
    -0.76
     JADX
    -0.75
    MigrationBuilder
    -0.75
    FieldBuilder
    -0.75
    XmlAccessType
    -0.75
    ⓧ
    -0.73
    POSITIVE LOGITS
     ENABLE
    0.67
     enable
    0.65
    enable
    0.63
    activate
    0.60
     switch
    0.60
     disable
    0.59
     activate
    0.58
     DISABLE
    0.58
     disables
    0.57
     activation
    0.55
    Act Density 0.109%

    No Known Activations