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

    Neuronpedia

    INDEX
    Explanations

    formula for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (,
    0.63
    ."),
    0.59
     включая
    0.59
    ských
    0.56
     ค่ะ
    0.55
     ().
    0.55
     产品
    0.54
     सीताराम
    0.54
    odnev
    0.54
    ."},
    0.54
    POSITIVE LOGITS
     permettant
    0.89
     allow
    0.82
     bunu
    0.82
     isso
    0.75
     permet
    0.74
     कुर्बानी
    0.74
     nudge
    0.72
     permettent
    0.72
     bring
    0.71
     same
    0.70
    Act Density 0.001%

    No Known Activations