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

    Neuronpedia

    INDEX
    Explanations

    ALMA, SQL expressions, code clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.30
     Сы
    0.29
     canoes
    0.29
    x
    0.28
     n
    0.27
    ah
    0.27
     Grecia
    0.27
    ales
    0.26
     element
    0.26
     fittings
    0.26
    POSITIVE LOGITS
    ناب
    0.31
     analisar
    0.30
    ｄ
    0.30
    徂
    0.29
     पढ़ेंगे
    0.28
    കൾ
    0.28
    нг
    0.27
     analisis
    0.27
    疤
    0.27
    writeHead
    0.27
    Act Density 0.066%

    No Known Activations