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

    Neuronpedia

    INDEX
    Explanations

    latex document closing brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱞ
    0.71
    𝒄
    0.68
    ित
    0.68
    ार
    0.65
     لوبو
    0.63
    oler
    0.61
    čky
    0.59
     使っ
    0.58
     cáo
    0.57
     atores
    0.57
    POSITIVE LOGITS
     or
    1.05
    in
    0.74
    s
    0.70
    ine
    0.69
    re
    0.68
    el
    0.67
    ↵
    0.66
    /
    0.66
    ham
    0.63
    n
    0.61
    Act Density 0.008%

    No Known Activations