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

    Neuronpedia

    INDEX
    Explanations

    Ludwig and associated names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дне
    0.41
     indeed
    0.41
     fron
    0.40
     Fron
    0.39
     macaroni
    0.38
     truly
    0.38
    Ordinate
    0.38
    indeed
    0.38
    qual
    0.38
    धुनिक
    0.38
    POSITIVE LOGITS
    acyj
    0.41
    önt
    0.41
    ्यूट
    0.41
    ):
    0.40
    ),],
    0.40
    폈
    0.38
    شت
    0.38
    öder
    0.38
     ежеднев
    0.38
     Wittgenstein
    0.37
    Act Density 0.001%

    No Known Activations