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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ſelves
    -0.98
     pleaſure
    -0.97
     Diſ
    -0.96
     Theſe
    -0.96
     ſche
    -0.94
     Monfieur
    -0.94
     itſelf
    -0.94
     Anſ
    -0.92
    QMetaType
    -0.91
    ſelf
    -0.91
    POSITIVE LOGITS
     the
    0.74
    <bos>
    0.63
     when
    0.55
     at
    0.54
     re
    0.54
     see
    0.52
     as
    0.51
     though
    0.50
     went
    0.50
     from
    0.49
    Act Density 0.168%

    No Known Activations