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

    Neuronpedia

    INDEX
    Explanations

    local variables and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veneers
    2.06
     kuti
    2.03
     tattoos
    1.89
     LOCCTR
    1.88
     pitfalls
    1.86
     crackdown
    1.84
     tweaks
    1.84
    车型
    1.81
    Presets
    1.77
     abnormalities
    1.76
    POSITIVE LOGITS
    ﺳ
    1.39
     déb
    1.38
    N
    1.36
    uição
    1.31
    a
    1.30
    ע
    1.25
     samping
    1.25
    ח
    1.22
    な
    1.20
    ા
    1.19
    Act Density 0.008%

    No Known Activations