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

    Neuronpedia

    INDEX
    Explanations

    several languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aging
    0.59
     goal
    0.58
    astype
    0.56
     multe
    0.55
     curved
    0.55
    ًا
    0.55
     pense
    0.55
     spacious
    0.55
     isos
    0.55
    als
    0.55
    POSITIVE LOGITS
    teborg
    0.63
    utica
    0.63
    اٹ
    0.62
    ocuk
    0.62
    cimentos
    0.61
     $*
    0.61
    fice
    0.60
    ֔
    0.60
    --’
    0.59
    逺
    0.59
    Act Density 0.009%

    No Known Activations