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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵
    -0.92
     (
    -0.83
     
    -0.79
    a
    -0.71
     I
    -0.70
     in
    -0.67
    -
    -0.66
     and
    -0.64
     E
    -0.63
     or
    -0.63
    POSITIVE LOGITS
     Reſ
    1.39
     Anſ
    1.35
     Houſe
    1.28
     Monfieur
    1.28
     Diſ
    1.27
     Мексичка
    1.25
     Majefty
    1.24
     Conſ
    1.19
     Efq
    1.17
     ་་
    1.16
    Act Density 0.311%

    No Known Activations