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

    Neuronpedia

    INDEX
    Explanations

    response, err

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Г
    1.16
    Е
    1.15
    Π
    1.13
    N
    1.10
    Ә
    1.09
    Ҳ
    1.08
    யா
    1.07
    Я
    1.07
    。
    1.06
    TL
    1.05
    POSITIVE LOGITS
    cita
    1.08
    kan
    1.05
     سازی
    1.01
    kon
    1.00
     Pública
    1.00
     Comercio
    0.99
     వారి
    0.98
     całym
    0.98
    ნიშ
    0.96
     झुक
    0.96
    Act Density 0.242%

    No Known Activations