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

    Neuronpedia

    INDEX
    Explanations

    asterisk or star symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.57
    i
    1.44
    es
    1.39
    ת
    1.35
    ت
    1.24
    ০
    1.12
    ی
    1.09
    া
    1.02
    e
    1.01
    y
    1.01
    POSITIVE LOGITS
     resorption
    0.68
    𝑂
    0.66
     Debit
    0.66
     infringe
    0.65
    ἆ
    0.64
     perfecting
    0.63
     abundantly
    0.63
    ö
    0.63
    lád
    0.62
     Велико
    0.62
    Act Density 1.253%

    No Known Activations