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

    Neuronpedia

    INDEX
    Explanations

    opportunities and potential outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sink
    0.46
    كتب
    0.43
    Sm
    0.42
    to
    0.41
     EDIT
    0.41
     العربي
    0.41
    م
    0.41
    touch
    0.40
    talk
    0.40
    KER
    0.40
    POSITIVE LOGITS
     স্বল্প
    0.46
     bào
    0.45
    <>();
    0.44
    hiddenMap
    0.43
    били
    0.41
     alcun
    0.40
    olução
    0.40
    วิทยา
    0.40
     Chancery
    0.39
     salon
    0.39
    Act Density 0.004%

    No Known Activations