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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ''.
    -0.07
     yaptı
    -0.07
    Store
    -0.07
     سبک
    -0.06
     artık
    -0.06
    ør
    -0.06
     değerli
    -0.06
     Roger
    -0.06
     Cheryl
    -0.06
    Through
    -0.06
    POSITIVE LOGITS
     آم
    0.07
     lid
    0.06
    лерг
    0.06
     específ
    0.06
    لاق
    0.06
    compatible
    0.06
    识
    0.06
    .Listen
    0.06
     минут
    0.06
     palace
    0.06
    Act Density 0.013%

    No Known Activations