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

    Neuronpedia

    INDEX
    Explanations

    probabilistic arguments and science

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    咗
    0.43
     близо
    0.39
    Wis
    0.38
     nearer
    0.37
    iją
    0.37
    空间
    0.36
    Localized
    0.36
    мна
    0.35
    iqu
    0.35
    anamh
    0.35
    POSITIVE LOGITS
     dov
    0.41
    ua
    0.41
     Argentina
    0.41
    пова
    0.39
     Patagonia
    0.39
     Rao
    0.38
     Ag
    0.38
     boca
    0.38
     Dream
    0.38
    centes
    0.38
    Act Density 0.000%

    No Known Activations