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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VU
    -0.08
    所谓
    -0.08
     ose
    -0.08
     wholes
    -0.08
     slučaju
    -0.08
    ుస్త
    -0.07
     Mohamed
    -0.07
     klient
    -0.07
    ર્ત
    -0.07
    ilishi
    -0.07
    POSITIVE LOGITS
    #↵
    0.09
    !↵↵↵
    0.09
    。↵↵↵
    0.08
    0.08
    ?↵↵↵
    0.08
    #↵↵
    0.08
    .↵↵↵↵↵↵
    0.08
    ?↵↵↵↵
    0.08
    :)↵↵
    0.08
     #↵↵
    0.08
    Act Density 0.106%
    No Known Activations