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

    Neuronpedia

    INDEX
    Explanations

    async functions returning Result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    龇
    0.43
    ุล
    0.43
    اشی
    0.39
    䢎
    0.39
    ότητας
    0.39
    𒈪
    0.39
    㝅
    0.39
    衵
    0.39
    䀘
    0.39
     ಬಹು
    0.39
    POSITIVE LOGITS
     Cris
    0.35
    ↵↵
    0.35
    Rena
    0.35
     W
    0.34
    Europe
    0.34
    orche
    0.34
     #
    0.33
    W
    0.33
    0.33
    ↵
    0.33
    Act Density 0.001%

    No Known Activations