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
     Wednesday
    -0.07
     ump
    -0.07
    .recycle
    -0.06
    _commit
    -0.06
     بانک
    -0.06
     Combat
    -0.06
    现场
    -0.06
     linh
    -0.06
    /grpc
    -0.06
    .gz
    -0.06
    POSITIVE LOGITS
    �
    0.07
    tabl
    0.07
    inee
    0.07
    verige
    0.06
    /vue
    0.06
     kurz
    0.06
    daf
    0.06
     enam
    0.06
     MATLAB
    0.06
    ッツ
    0.06
    Act Density 0.037%

    No Known Activations