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

    Neuronpedia

    INDEX
    Explanations

    >&

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chairs
    -0.07
     смер
    -0.06
     Canton
    -0.06
     Ful
    -0.06
     vzdělávání
    -0.06
    �
    -0.06
     Kate
    -0.06
     Billy
    -0.06
     shortly
    -0.05
     Κύπ
    -0.05
    POSITIVE LOGITS
    ær
    0.07
     μεγά
    0.07
    earing
    0.07
    Framework
    0.06
    меть
    0.06
    erde
    0.06
    _question
    0.06
     manic
    0.06
    .ask
    0.06
     Gay
    0.06
    Act Density 0.000%

    No Known Activations