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

    Neuronpedia

    INDEX
    Explanations

    fantastic and great words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.38
    ’
    0.36
    C
    0.36
    0.32
    できる
    0.29
     कीमत
    0.27
     cach
    0.26
     urea
    0.26
     रात
    0.25
    that
    0.25
    POSITIVE LOGITS
     excelente
    0.33
    ዎቹ
    0.33
     জনপ্রিয়
    0.32
     молоде
    0.32
    ە
    0.32
    anneer
    0.31
     гульнявыя
    0.31
     👌
    0.31
     allez
    0.30
    น์โหลด
    0.30
    Act Density 0.312%

    No Known Activations