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

    Neuronpedia

    INDEX
    Explanations

    substitute or optional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ออกมา
    0.47
    З
    0.47
    Յ
    0.43
    cod
    0.42
    ไป
    0.42
    䉼
    0.42
    ห
    0.41
    ั้น
    0.41
    结论
    0.41
    íš
    0.40
    POSITIVE LOGITS
     fundamentos
    0.54
     عدم
    0.49
     varje
    0.46
     alimentos
    0.46
     aspectos
    0.45
     questões
    0.44
     sabores
    0.43
     先
    0.42
     Verbesser
    0.42
     చివరి
    0.42
    Act Density 0.015%

    No Known Activations