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

    Neuronpedia

    INDEX
    Explanations

    joined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    港股
    -0.08
    在京
    -0.07
     เม
    -0.07
    放假
    -0.07
     reduction
    -0.07
     Belgium
    -0.07
    cstdint
    -0.07
     Silent
    -0.07
     Philly
    -0.07
    arrays
    -0.07
    POSITIVE LOGITS
    實際
    0.08
     Cast
    0.07
    �
    0.07
     tied
    0.06
     prompted
    0.06
    徑
    0.06
     המצב
    0.06
    贿
    0.06
     условия
    0.06
    땨
    0.06
    Act Density 0.099%

    No Known Activations