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

    Neuronpedia

    INDEX
    Explanations

    a lot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     constitué
    1.29
    ווה
    1.28
     aka
    1.17
     przyjem
    1.15
     magnifique
    1.14
     composto
    1.13
     Influ
    1.13
     🥰
    1.12
     vài
    1.12
    zäh
    1.12
    POSITIVE LOGITS
    规定的
    1.12
    на
    1.01
     allowable
    1.00
    検査
    0.99
    判定
    0.96
    ﾝ
    0.93
     Б
    0.91
    НА
    0.91
     APPLE
    0.91
    最新的
    0.91
    Act Density 0.000%

    No Known Activations