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

    Neuronpedia

    INDEX
    Explanations

    sequence processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dallo
    0.46
    pares
    0.44
    closest
    0.44
    Closest
    0.41
     compon
    0.41
     diagon
    0.41
    tug
    0.40
    際に
    0.40
    promo
    0.39
     القيم
    0.39
    POSITIVE LOGITS
    尼亚
    0.42
    çou
    0.42
     Untersuchung
    0.41
    UES
    0.41
    들을
    0.40
    рі
    0.40
     educating
    0.40
    azam
    0.40
     دنیا
    0.40
     শুন
    0.40
    Act Density 0.002%

    No Known Activations