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

    Neuronpedia

    INDEX
    Explanations

    criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tide
    -0.07
     fraternity
    -0.07
     enh
    -0.07
     humidity
    -0.07
     gegen
    -0.07
    :UIButtonTypeCustom
    -0.07
    (edges
    -0.06
    ([...
    -0.06
    ूड
    -0.06
     nesting
    -0.06
    POSITIVE LOGITS
    London
    0.07
     Wealth
    0.06
    afka
    0.06
    .kafka
    0.06
    what
    0.06
    iliated
    0.06
     دنیا
    0.06
    ercises
    0.06
     cuckold
    0.06
    esi
    0.06
    Act Density 0.000%

    No Known Activations