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

    Neuronpedia

    INDEX
    Explanations

    help me figure out asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    re
    0.35
    k
    0.35
    리
    0.35
    b
    0.34
    s
    0.34
    iad
    0.32
     was
    0.32
    ED
    0.32
     smiled
    0.31
     embl
    0.31
    POSITIVE LOGITS
    従って
    0.25
    น
    0.25
    他的
    0.25
    弛
    0.24
     WANT
    0.23
    வ்வேறு
    0.23
    ุ
    0.23
     पैदा
    0.22
    ห
    0.22
    眉
    0.22
    Act Density 0.259%

    No Known Activations