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

    Neuronpedia

    INDEX
    Explanations

    stating things

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мно
    0.66
     lágrimas
    0.61
     Rennen
    0.60
     algumas
    0.58
    готов
    0.58
     allt
    0.57
    funcs
    0.56
    otra
    0.56
    rocities
    0.56
    преки
    0.56
    POSITIVE LOGITS
     upholding
    0.77
     upheld
    0.77
     stating
    0.75
     satisfies
    0.74
     satisfactorily
    0.74
     attains
    0.73
     ruling
    0.70
     declaring
    0.68
     withstood
    0.68
     uphold
    0.67
    Act Density 0.000%

    No Known Activations