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

    Neuronpedia

    INDEX
    Explanations

    sales and sales figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idin
    0.63
    itches
    0.61
    idunt
    0.59
    íd
    0.58
    許多
    0.57
    icht
    0.56
    ッコ
    0.56
    是
    0.55
    gt
    0.54
    는
    0.54
    POSITIVE LOGITS
    u
    0.71
    ड
    0.62
    डीए
    0.61
    SBP
    0.60
     начну
    0.59
     ."
    0.58
    a
    0.58
    spoken
    0.57
    weaving
    0.56
    D
    0.56
    Act Density 0.001%

    No Known Activations