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

    Neuronpedia

    INDEX
    Explanations

    alphabet, families, or empire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म्मेदारी
    0.52
    ቺ
    0.48
     цену
    0.47
     Promise
    0.47
     inputValue
    0.47
     MDS
    0.47
     سعر
    0.47
    价格
    0.46
     가격
    0.46
     ticketing
    0.46
    POSITIVE LOGITS
    f
    0.48
    yth
    0.47
    h
    0.47
     doth
    0.45
     حی
    0.44
    lind
    0.43
    Diffuse
    0.43
     empire
    0.42
    Alphabet
    0.42
    families
    0.42
    Act Density 0.000%

    No Known Activations