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

    Neuronpedia

    INDEX
    Explanations

    probability problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buz
    -0.07
    説
    -0.07
     shm
    -0.06
    width
    -0.06
    ость
    -0.06
     作
    -0.06
     noon
    -0.06
    ']}</
    -0.06
     sucht
    -0.06
    )$/
    -0.06
    POSITIVE LOGITS
     MATLAB
    0.07
    選択
    0.07
     Levine
    0.07
    LONG
    0.06
     candles
    0.06
     Presented
    0.06
    _MAT
    0.06
     fingerprint
    0.06
    理由
    0.06
     Dos
    0.06
    Act Density 0.001%

    No Known Activations