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

    Neuronpedia

    INDEX
    Explanations

    distribute, simplify, solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atteinte
    0.93
    IENTE
    0.87
    У
    0.86
    తో
    0.85
    டன்
    0.83
    ATHER
    0.81
    cele
    0.81
     Πολ
    0.81
    CEL
    0.79
    PRES
    0.77
    POSITIVE LOGITS
     servings
    0.99
     Dany
    0.84
     said
    0.84
     western
    0.84
    us
    0.83
    ি
    0.82
     zon
    0.82
     gra
    0.80
    y
    0.80
     medici
    0.79
    Act Density 0.000%

    No Known Activations