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

    Neuronpedia

    INDEX
    Explanations

    minimum and maximum values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     identique
    0.48
    スル
    0.47
    Кон
    0.46
    بیر
    0.46
    店舗
    0.44
     identiques
    0.43
     sekar
    0.43
    ПР
    0.43
     kéo
    0.43
     강조
    0.42
    POSITIVE LOGITS
    jt
    0.51
     Drilling
    0.48
    ent
    0.47
    ç
    0.47
     CL
    0.47
     Removed
    0.46
    et
    0.46
     स्ने
    0.45
     Exc
    0.45
     Systems
    0.45
    Act Density 0.002%

    No Known Activations