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

    Neuronpedia

    INDEX
    Explanations

    provides a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.08
    ता
    1.00
    gever
    0.99
    enyl
    0.97
    otherapeutic
    0.97
     fraught
    0.96
    した
    0.95
    Damn
    0.95
    luoromethyl
    0.94
     bersifat
    0.94
    POSITIVE LOGITS
     Aula
    1.12
    of
    1.08
    ło
    1.04
     fala
    0.99
     licz
    0.95
    v
    0.94
    این
    0.94
     dino
    0.94
    dados
    0.93
    десят
    0.93
    Act Density 0.001%

    No Known Activations