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

    Neuronpedia

    INDEX
    Explanations

    put the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avuto
    0.87
     имели
    0.80
     акча
    0.80
    했습니다
    0.79
     ribu
    0.78
    0.78
     hanno
    0.76
    ాల్
    0.75
     avevano
    0.75
    贼
    0.75
    POSITIVE LOGITS
     Já
    0.77
     Expertise
    0.77
     Últ
    0.77
     Vibr
    0.76
    istics
    0.74
    Gest
    0.73
    Psych
    0.73
    鯵
    0.73
     Particular
    0.73
     Announcement
    0.72
    Act Density 0.004%

    No Known Activations