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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그는
    0.38
     उसने
    0.37
     คุณ
    0.36
     त्याने
    0.36
     jego
    0.35
     ඔහු
    0.35
     उसे
    0.34
     Kontext
    0.34
     അയാള
    0.34
    あなたは
    0.33
    POSITIVE LOGITS
    tcpHeader
    0.29
    បើ
    0.29
     our
    0.28
     unison
    0.27
     gali
    0.27
    nut
    0.26
    entries
    0.26
     useSelector
    0.26
    がたくさん
    0.26
    溦
    0.25
    Act Density 0.087%

    No Known Activations