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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跡
    -0.07
     shin
    -0.07
    овым
    -0.06
    _fu
    -0.06
    Tre
    -0.06
     ful
    -0.06
    ù
    -0.06
    בס
    -0.06
    |null
    -0.06
     thú
    -0.06
    POSITIVE LOGITS
     ואז
    0.07
     Eva
    0.07
    團隊
    0.07
    俺
    0.07
    利益
    0.07
     الرحمن
    0.07
     controlling
    0.06
     Seventh
    0.06
     opportun
    0.06
     Nine
    0.06
    Act Density 0.001%

    No Known Activations