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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fh
    -0.06
     cautioned
    -0.06
     ringing
    -0.06
    dataset
    -0.06
     возраста
    -0.06
     Singer
    -0.06
     Pasta
    -0.06
    UGIN
    -0.06
     dane
    -0.06
     dell
    -0.06
    POSITIVE LOGITS
    ♠
    0.07
     Exists
    0.06
    -minute
    0.06
     Unblock
    0.06
    ##
    0.06
     переш
    0.06
     sess
    0.06
     Можно
    0.06
     imaginable
    0.06
    bps
    0.06
    Act Density 0.000%

    No Known Activations