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

    Neuronpedia

    INDEX
    Explanations

    stable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .invalidate
    -0.07
     جزء
    -0.07
    BY
    -0.07
    άλυ
    -0.06
    杰
    -0.06
    REGION
    -0.06
    iers
    -0.06
    board
    -0.06
    HELP
    -0.06
     tons
    -0.06
    POSITIVE LOGITS
     非
    0.06
     光
    0.06
     最
    0.06
    ToLocal
    0.06
     smoker
    0.06
    ');?>
    0.06
    -Semit
    0.06
    .hu
    0.06
     Explos
    0.06
    uant
    0.06
    Act Density 0.002%

    No Known Activations