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

    Neuronpedia

    INDEX
    Explanations

    problems

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ammed
    0.73
    جموع
    0.68
     keySchedule
    0.65
    amed
    0.64
     Soldaten
    0.63
    enzione
    0.63
    літи
    0.62
     نړ
    0.62
    ramid
    0.61
    azze
    0.60
    POSITIVE LOGITS
     была
    0.66
     problems
    0.66
     был
    0.66
     Мы
    0.61
     contagion
    0.59
     autonomy
    0.58
     was
    0.57
     мы
    0.57
     actualizaciones
    0.56
     હતો
    0.56
    Act Density 0.000%

    No Known Activations