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

    Neuronpedia

    INDEX
    Explanations

    asking for elaboration or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bases
    0.83
     First
    0.81
     Strategy
    0.77
     Question
    0.73
     overwritten
    0.73
     Property
    0.71
     Environment
    0.71
     basis
    0.70
     bases
    0.70
     Studios
    0.68
    POSITIVE LOGITS
     іх
    0.80
    mostrar
    0.74
     odnosno
    0.74
     njima
    0.72
     فروغ
    0.72
     paroi
    0.72
     wünschen
    0.71
    Ч
    0.71
     آنان
    0.71
    cargar
    0.71
    Act Density 0.013%

    No Known Activations