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

    Neuronpedia

    INDEX
    Explanations

    degrees of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mlij
    0.74
    േഷ
    0.71
    𝓂
    0.71
     растения
    0.71
    คนที่
    0.70
    𝗬
    0.70
     შესაძ
    0.69
    𝐋
    0.67
    azze
    0.66
     가능
    0.66
    POSITIVE LOGITS
     of
    2.05
     de
    1.75
     Of
    1.54
    of
    1.52
     ഓഫ്
    1.43
    Of
    1.42
     ఆఫ్
    1.35
     של
    1.30
     ऑफ
    1.25
     OF
    1.24
    Act Density 0.441%

    No Known Activations