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

    Neuronpedia

    INDEX
    Explanations

    talents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -1.06
     myſelf
    -1.03
     Monfieur
    -0.94
     Anſ
    -0.93
     Houſe
    -0.91
     reaſon
    -0.87
     houſe
    -0.87
     चीज़ों
    -0.84
     itſelf
    -0.84
    ſelf
    -0.84
    POSITIVE LOGITS
     of
    0.59
     hindurch
    0.57
    ValueStyle
    0.55
    h
    0.47
    şağı
    0.47
     --
    0.47
     mantenerse
    0.47
     I
    0.46
     in
    0.46
     as
    0.46
    Act Density 1.719%

    No Known Activations