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

    Neuronpedia

    INDEX
    Explanations

    choosing platform or selecting voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स
    1.03
    s
    0.87
    ्स
    0.85
    ات
    0.84
    Istituto
    0.78
    У
    0.77
    Cookies
    0.76
    Χ
    0.74
    Dieses
    0.74
    د
    0.73
    POSITIVE LOGITS
    сы
    0.86
    чное
    0.80
     зарабо
    0.79
     configurational
    0.79
    ỏi
    0.73
    ън
    0.73
     downright
    0.72
    aggregation
    0.72
     arrec
    0.72
    ashi
    0.72
    Act Density 0.001%

    No Known Activations