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

    Neuronpedia

    INDEX
    Explanations

    Archives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encrypt
    -0.08
     gim
    -0.07
    .getLogger
    -0.07
     Sherlock
    -0.07
    bots
    -0.06
     prox
    -0.06
     Muj
    -0.06
     gó
    -0.06
     coeff
    -0.06
    ädchen
    -0.06
    POSITIVE LOGITS
     Archives
    0.10
     chí
    0.07
     SS
    0.07
    ready
    0.07
    CGFloat
    0.06
    最后
    0.06
    ????
    0.06
     Exceptions
    0.06
    啊
    0.06
    YN
    0.06
    Act Density 0.001%

    No Known Activations