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

    Neuronpedia

    INDEX
    Explanations

    NSLog

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ombine
    -0.07
    raquo
    -0.07
    .What
    -0.07
    ые
    -0.06
    ندی
    -0.06
     rests
    -0.06
     Override
    -0.06
    reta
    -0.06
    comma
    -0.06
    aret
    -0.06
    POSITIVE LOGITS
     Som
    0.07
    골
    0.07
    金
    0.07
     Bd
    0.07
    SIG
    0.06
     speedy
    0.06
    Rom
    0.06
     معدن
    0.06
     Review
    0.06
     glamour
    0.06
    Act Density 0.001%

    No Known Activations