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

    Neuronpedia

    INDEX
    Explanations

    don't miss out, don't skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    儡
    1.13
    ﻡ
    1.01
    cyon
    1.01
    OUIS
    1.00
     pháp
    0.98
    之下
    0.97
     muit
    0.96
     schizophrenia
    0.96
     competitively
    0.95
     misalkan
    0.95
    POSITIVE LOGITS
    ar
    1.22
    जागरण
    1.10
    at
    0.98
    К
    0.97
    Cream
    0.97
     électronique
    0.95
    us
    0.94
    Jetzt
    0.92
    InvalidArgument
    0.91
     antérieur
    0.90
    Act Density 0.049%

    No Known Activations