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

    Neuronpedia

    INDEX
    Explanations

    language and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ——
    0.98
    —
    0.92
    --
    0.85
    ----
    0.78
    ~
    0.75
    ─
    0.75
    [-]
    0.74
     --
    0.70
    [\
    0.70
    ~~
    0.69
    POSITIVE LOGITS
    讵
    1.67
    liono
    1.65
     살펴보도록
    1.64
     هنتكلم
    1.62
    欲しい
    1.61
     אח
    1.61
    kipun
    1.61
    avljen
    1.60
     الاج
    1.60
    きたいと思います
    1.60
    Act Density 0.001%

    No Known Activations