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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વિભાગ
    0.41
    强
    0.41
    ቻል
    0.39
    ៥
    0.39
     強
    0.39
    강
    0.39
    lbrakk
    0.38
    ৤
    0.38
    <unused1010>
    0.37
     자체
    0.36
    POSITIVE LOGITS
     nodding
    0.37
     writ
    0.37
    مش
    0.36
     amendments
    0.35
     whiche
    0.35
     सहमत
    0.35
     Anci
    0.35
     communes
    0.34
    writ
    0.34
     impug
    0.34
    Act Density 0.000%

    No Known Activations