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

    Neuronpedia

    INDEX
    Explanations

    code function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    าน
    0.40
     хода
    0.39
    ๓
    0.38
    нина
    0.38
    Easter
    0.37
    ታት
    0.36
    situ
    0.36
    Produto
    0.35
     Ephesians
    0.35
    宇
    0.35
    POSITIVE LOGITS
    函数
    0.60
     func
    0.59
     function
    0.58
     функцию
    0.57
     функция
    0.56
    function
    0.55
     функ
    0.54
     fungsi
    0.51
    функ
    0.50
     함수
    0.50
    Act Density 0.097%

    No Known Activations