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

    Neuronpedia

    INDEX
    Explanations

    monetary units and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     аспек
    0.86
     Anosov
    0.80
     Mant
    0.79
     Tutto
    0.79
     Raman
    0.76
     singers
    0.71
    𝗗
    0.71
     CONDITIONS
    0.71
     Após
    0.71
     heralded
    0.71
    POSITIVE LOGITS
    ى
    0.95
    inator
    0.90
    ки
    0.87
    iw
    0.84
    ným
    0.84
    ai
    0.83
    ف
    0.82
    in
    0.79
    ir
    0.79
    то
    0.75
    Act Density 0.001%

    No Known Activations