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

    Neuronpedia

    INDEX
    Explanations

    monthly interest rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computations
    0.82
    ಖ
    0.79
     balloons
    0.75
     calcule
    0.74
    mland
    0.73
    गार
    0.73
     households
    0.71
    工业
    0.70
    }_{+
    0.69
     सौरभ
    0.69
    POSITIVE LOGITS
     versión
    0.73
    さすが
    0.69
    athe
    0.67
     version
    0.66
    ლა
    0.66
     zase
    0.65
     versione
    0.65
    enka
    0.65
     версия
    0.65
    反而
    0.65
    Act Density 0.001%

    No Known Activations