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

    Neuronpedia

    INDEX
    Explanations

    explaining things in simple terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulk
    0.53
    bets
    0.46
    gw
    0.45
    cional
    0.45
    potential
    0.43
    कर
    0.43
     सिलसिला
    0.42
    ámicas
    0.42
    par
    0.41
    uses
    0.41
    POSITIVE LOGITS
    Storia
    0.46
    院长
    0.45
     psychiat
    0.43
     hyst
    0.43
     verzek
    0.43
    客厅
    0.43
    电路
    0.42
     erreurs
    0.41
     పరిస్థి
    0.41
     alapján
    0.41
    Act Density 0.007%

    No Known Activations