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

    Neuronpedia

    INDEX
    Explanations

    locations and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     또는
    1.08
     অবশ্যই
    1.06
     &/
    1.01
     ছাড়াই
    0.97
     포함
    0.95
     다양한
    0.94
     أو
    0.94
     tamaños
    0.94
     किंवा
    0.94
     ویژگی
    0.92
    POSITIVE LOGITS
    when
    0.69
     havia
    0.69
     when
    0.66
    await
    0.63
    next
    0.62
     next
    0.62
     atan
    0.60
     quando
    0.59
     paru
    0.56
    abe
    0.56
    Act Density 0.168%

    No Known Activations