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

    Neuronpedia

    INDEX
    Explanations

    phrase validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.54
    ur
    0.52
    is
    0.46
    ap
    0.46
     plaus
    0.42
     pares
    0.42
     pneus
    0.42
    ोदय
    0.41
    on
    0.41
    agor
    0.41
    POSITIVE LOGITS
     &/
    0.49
     '':
    0.48
     Võ
    0.46
    мом
    0.45
     ò
    0.43
     judgments
    0.42
    badges
    0.42
     SupCt
    0.42
    可能です
    0.41
     $'
    0.41
    Act Density 0.001%

    No Known Activations