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

    Neuronpedia

    INDEX
    Explanations

    legal protection, liability insurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ecause
    0.48
    approximately
    0.48
    सही
    0.48
    정책
    0.47
    exceptional
    0.47
     Ashby
    0.47
    돠
    0.46
    少なく
    0.45
    താണ്
    0.45
    सूचित
    0.45
    POSITIVE LOGITS
     खून
    0.45
     دين
    0.45
     منہ
    0.45
    驯
    0.44
     التع
    0.44
     verz
    0.43
     frut
    0.43
     đựng
    0.43
    馴
    0.43
    űr
    0.42
    Act Density 0.002%

    No Known Activations