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

    Neuronpedia

    INDEX
    Explanations

    code diff markers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
     itſelf
    -0.87
     Brind
    -0.78
     iſt
    -0.77
     Jefus
    -0.76
     myſelf
    -0.75
     Theſe
    -0.75
     himſelf
    -0.73
     Diſ
    -0.73
     Heere
    -0.73
    POSITIVE LOGITS
     @@
    2.03
    @@
    1.02
     Вікіпе
    0.69
    setViewportView
    0.68
    >@
    0.62
     Sewell
    0.60
    >{@
    0.60
    EndContext
    0.58
     át
    0.57
    __()
    0.56
    Act Density 0.002%

    No Known Activations