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

    Neuronpedia

    INDEX
    Explanations

    advertisements and forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.80
     =
    0.79
    by
    0.79
     מ
    0.77
    ES
    0.73
     -
    0.71
     )
    0.69
    TE
    0.68
    ED
    0.68
     ,
    0.66
    POSITIVE LOGITS
    ан
    0.74
    ρων
    0.73
     enjeux
    0.71
    лле
    0.68
    ях
    0.67
    ст
    0.66
    <0xB5>
    0.66
    чее
    0.63
     cajas
    0.63
    Methylsulfanyl
    0.63
    Act Density 0.000%

    No Known Activations