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

    Neuronpedia

    INDEX
    Explanations

    sentencing reform

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ၀
    0.74
     fit
    0.70
     flocks
    0.68
    সাইন
    0.67
     Fit
    0.66
     المجال
    0.64
     visión
    0.63
    Fit
    0.63
     sphere
    0.63
     visione
    0.62
    POSITIVE LOGITS
    otal
    0.70
     Verpack
    0.68
    镇
    0.67
    藍
    0.66
     Zentral
    0.65
    Tu
    0.63
     tu
    0.63
    Recover
    0.62
     janu
    0.62
     डेवलप
    0.62
    Act Density 0.000%

    No Known Activations