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

    Neuronpedia

    INDEX
    Explanations

    Sony and Marvel universes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.65
    ي
    0.61
    ли
    0.59
     функция
    0.58
     फॉर
    0.57
     диапа
    0.54
    فن
    0.52
     пакет
    0.52
    лари
    0.51
    ीकरण
    0.51
    POSITIVE LOGITS
    ש
    0.76
    s
    0.70
    ن
    0.61
    س
    0.58
    না
    0.50
    ate
    0.50
    き
    0.49
    ﺎ
    0.49
    ="
    0.48
    }
    0.48
    Act Density 0.001%

    No Known Activations