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

    Neuronpedia

    INDEX
    Explanations

    numbers near 132

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    967
    -0.08
    941
    -0.07
    48
    -0.07
     poly
    -0.07
     pool
    -0.07
     dividend
    -0.07
     seven
    -0.07
     Cricket
    -0.07
     compar
    -0.06
     dip
    -0.06
    POSITIVE LOGITS
    132
    0.07
    133
    0.07
     IMessage
    0.07
     includes
    0.07
    cales
    0.07
    Encoded
    0.06
    134
    0.06
     [{
    0.06
    _EC
    0.06
    结构
    0.06
    Act Density 0.014%

    No Known Activations