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

    Neuronpedia

    INDEX
    Explanations

    offer, selection, waste, apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    buje
    0.46
    不然
    0.46
    ي
    0.45
    و
    0.45
    resión
    0.44
    وحة
    0.43
    盾
    0.43
    oloč
    0.42
    新
    0.41
    ني
    0.41
    POSITIVE LOGITS
     Bourne
    0.49
     Reference
    0.48
    pN
    0.48
     Piccolo
    0.47
     walter
    0.47
     correspond
    0.47
    ඡ
    0.46
     Source
    0.46
     tonal
    0.46
     Warhammer
    0.46
    Act Density 0.000%

    No Known Activations