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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     more
    -0.81
     or
    -0.71
     an
    -0.69
     a
    -0.68
     the
    -0.67
     some
    -0.63
     
    -0.63
     que
    -0.60
     más
    -0.55
     Ave
    -0.54
    POSITIVE LOGITS
     ་་
    1.06
     raiſ
    1.04
     ―――――
    1.02
     Shakspeare
    1.00
     itſelf
    0.98
     pleaſure
    0.94
     doubtnut
    0.94
     purpoſe
    0.93
    جغرافيا
    0.93
    PreferredItem
    0.91
    Act Density 0.095%

    No Known Activations