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

    Neuronpedia

    INDEX
    Explanations

    Important notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐒
    1.13
     méridionale
    1.10
    oning
    1.04
     ennemis
    1.04
    но
    1.03
    𝐟
    1.03
    ал
    1.02
    реди
    1.02
    easing
    1.01
    者
    1.01
    POSITIVE LOGITS
    ler
    1.05
    ps
    1.02
    注意事項
    1.00
    ts
    0.99
    man
    0.97
    tt
    0.94
    nt
    0.92
    ص
    0.91
    ".
    0.90
     übers
    0.89
    Act Density 0.413%

    No Known Activations