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

    Neuronpedia

    INDEX
    Explanations

    scientific language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -2.16
     myſelf
    -1.97
     Monfieur
    -1.95
     Efq
    -1.94
     Jefus
    -1.88
     Anſ
    -1.84
     Houſe
    -1.80
     Theſe
    -1.78
     ―――――
    -1.73
     doubtnut
    -1.69
    POSITIVE LOGITS
    <eos>
    1.10
    '
    1.08
    .
    1.05
    ’
    0.95
     
    0.93
    li
    0.91
    n
    0.87
    is
    0.85
    -
    0.84
     (
    0.84
    Act Density 0.127%

    No Known Activations