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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RU
    -0.06
    rede
    -0.06
    ンプ
    -0.06
    .Url
    -0.06
    umo
    -0.06
    REAK
    -0.06
    Disp
    -0.06
     Somebody
    -0.06
     справа
    -0.06
     +#
    -0.06
    POSITIVE LOGITS
    .Absolute
    0.08
    Restr
    0.07
     영향
    0.07
    .GetProperty
    0.07
     employers
    0.06
    .ex
    0.06
    .Acc
    0.06
     implic
    0.06
     deductions
    0.06
    襲
    0.06
    Act Density 0.010%

    No Known Activations