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

    Neuronpedia

    INDEX
    Explanations

    as a decimal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cotton
    0.42
     Calcul
    0.41
     strane
    0.40
    ียง
    0.39
     Willem
    0.38
    绷
    0.38
     soci
    0.38
     Close
    0.38
    দূ
    0.38
     decode
    0.37
    POSITIVE LOGITS
     decimal
    0.93
     decimals
    0.89
    decimal
    0.84
    Decimal
    0.78
     Decimal
    0.74
    decimals
    0.70
     DECIMAL
    0.70
     दशमलव
    0.63
    小数
    0.62
     দশমিক
    0.55
    Act Density 0.001%

    No Known Activations