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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Meanwhile
    -0.07
    変更
    -0.06
    dehyde
    -0.06
    cnt
    -0.06
     Normal
    -0.06
    ารย
    -0.06
    .nano
    -0.06
     Tata
    -0.06
     Yön
    -0.06
     Honor
    -0.06
    POSITIVE LOGITS
    лини
    0.07
    .out
    0.07
    -expression
    0.07
     wiki
    0.07
    ку
    0.06
     suffering
    0.06
    exchange
    0.06
     clin
    0.06
    .Free
    0.06
    _remove
    0.06
    Act Density 0.037%

    No Known Activations