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
    .lastIndexOf
    -0.07
     всей
    -0.07
     Mit
    -0.06
     subTitle
    -0.06
    _COMMIT
    -0.06
    “For
    -0.06
    .theta
    -0.06
     emin
    -0.06
    GroupName
    -0.06
     Noticed
    -0.06
    POSITIVE LOGITS
     ascii
    0.08
    CREASE
    0.07
    ich
    0.06
    凡
    0.06
    Fecha
    0.06
     사이트
    0.06
    堡
    0.06
     Palace
    0.06
    賽
    0.06
     exceeding
    0.06
    Act Density 0.005%

    No Known Activations