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

    Neuronpedia

    INDEX
    Explanations

    processor for preparing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ам
    0.46
    idis
    0.41
    lessis
    0.41
     existential
    0.40
     ensures
    0.40
    லீ
    0.39
    alam
    0.38
    ausal
    0.38
    yra
    0.37
    窿
    0.37
    POSITIVE LOGITS
     come
    0.40
     കണ
    0.39
     وقد
    0.39
    Santo
    0.39
     arn
    0.38
     Higher
    0.38
    Hight
    0.38
     Have
    0.37
    जा
    0.37
     have
    0.37
    Act Density 0.000%

    No Known Activations