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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нием
    1.22
    𝘵
    1.20
    mettre
    1.17
    いろんな
    1.17
    siniz
    1.14
     leggere
    1.13
    𝐩
    1.10
    ли
    1.07
     ı
    1.05
     interni
    1.05
    POSITIVE LOGITS
    िक
    1.12
    ,
    0.88
     (
    0.85
    /
    0.83
     subtracted
    0.82
    (
    0.82
     delusions
    0.80
     outskirts
    0.79
     carelessly
    0.78
    ok
    0.77
    Act Density 0.013%

    No Known Activations