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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    עצמאי
    -0.07
    dź
    -0.07
    heed
    -0.06
     składa
    -0.06
     Fletcher
    -0.06
    断裂
    -0.06
    tical
    -0.06
    ignite
    -0.06
     Magnum
    -0.06
    amar
    -0.06
    POSITIVE LOGITS
    dba
    0.07
    演奏
    0.07
     ribs
    0.07
    ☮
    0.07
    圯
    0.07
    _db
    0.07
     affect
    0.07
    收到了
    0.07
    限时
    0.06
     inaugur
    0.06
    Act Density 0.001%

    No Known Activations