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

    Neuronpedia

    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ainfi
    -1.08
     Majefty
    -1.07
     myſelf
    -1.02
     ་་
    -0.95
     Anſ
    -0.95
     Theſe
    -0.94
     Monfieur
    -0.94
     auffi
    -0.93
     Cæsar
    -0.93
     ſeveral
    -0.93
    POSITIVE LOGITS
     
    0.78
     C
    0.68
     .
    0.66
     In
    0.66
     in
    0.66
     -
    0.65
     '
    0.65
     A
    0.65
    ,
    0.65
     L
    0.64
    Act Density 1.586%

    No Known Activations