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

    Neuronpedia

    INDEX
    Explanations

    product configurator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     なさい
    0.38
    Idea
    0.36
    טת
    0.36
     рода
    0.35
    ್ಟ
    0.34
    Handler
    0.34
     ഭ
    0.34
    ಬ್
    0.34
    ש
    0.33
    ט
    0.33
    POSITIVE LOGITS
    лығы
    0.39
     Veuillez
    0.36
    ऱ्यावर
    0.35
     vọng
    0.34
     Buick
    0.34
    ————————————————
    0.33
    нович
    0.33
     sèche
    0.33
     aura
    0.33
     puțin
    0.33
    Act Density 0.073%

    No Known Activations