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

    Neuronpedia

    INDEX
    Explanations

    exploit, exploits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ষ
    0.70
    ი
    0.66
     व्यक्ती
    0.66
     يد
    0.65
    ಣೆ
    0.64
    國家
    0.63
    啟
    0.61
    rown
    0.60
    SELF
    0.60
    jších
    0.59
    POSITIVE LOGITS
    ice
    0.69
    ong
    0.61
    winter
    0.61
    leh
    0.60
    imba
    0.60
    mot
    0.58
    oot
    0.58
     ionized
    0.56
    empre
    0.56
    деги
    0.55
    Act Density 0.148%

    No Known Activations