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

    Neuronpedia

    INDEX
    Explanations

    energy contains gasoline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мы
    0.85
    椷
    0.83
     সহ
    0.81
    exc
    0.81
    calcul
    0.80
     รี
    0.80
     мы
    0.77
    give
    0.77
    алы
    0.75
     เจ
    0.75
    POSITIVE LOGITS
    }:=
    0.79
     couleurs
    0.78
     principales
    0.76
     endroits
    0.75
     zéro
    0.73
     naturelle
    0.72
     spéciales
    0.72
     amené
    0.72
    𝄞
    0.70
    رب
    0.68
    Act Density 0.000%

    No Known Activations