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

    Neuronpedia

    INDEX
    Explanations

    discussing context limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ልዩ
    0.43
    Downtown
    0.41
    ъм
    0.39
    اٹ
    0.39
    incón
    0.39
     ప్రత్యేక
    0.38
    ્ટ
    0.38
    Trước
    0.38
    ्ञ
    0.38
     مقار
    0.38
    POSITIVE LOGITS
     forcing
    0.40
     rapidly
    0.38
     wipes
    0.37
     failings
    0.37
     proliferating
    0.37
     rapid
    0.36
    rocities
    0.36
     complesso
    0.36
     massac
    0.35
     쭉
    0.35
    Act Density 0.029%

    No Known Activations