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

    Neuronpedia

    INDEX
    Explanations

    opening and closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slides
    1.78
    |\
    1.76
    seeker
    1.69
    ات
    1.62
    ㄷ
    1.62
     problemi
    1.54
    Chọn
    1.54
    എസ്
    1.52
     editText
    1.51
     magnetores
    1.51
    POSITIVE LOGITS
    ें
    2.10
    ం
    2.06
    ا
    1.95
    że
    1.93
    요
    1.84
    ו
    1.83
    लिये
    1.79
    ো
    1.79
    al
    1.79
    اً
    1.74
    Act Density 0.000%

    No Known Activations