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

    Neuronpedia

    INDEX
    Explanations

    an unprecedented, susceptible, increased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scho
    0.52
     Dieser
    0.47
     sko
    0.43
     schle
    0.40
    전자
    0.40
     پیس
    0.39
    ียว
    0.39
    Lr
    0.38
    暌
    0.38
    Dto
    0.38
    POSITIVE LOGITS
     выпа
    0.39
    ミネ
    0.38
    Ming
    0.37
    XPATH
    0.37
     µ
    0.36
    DISPLAY
    0.36
     deacetyl
    0.36
    рик
    0.36
    mii
    0.34
     intercepted
    0.34
    Act Density 0.002%

    No Known Activations