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

    Neuronpedia

    INDEX
    Explanations

    Lovecraftian stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    舞蹈
    0.48
    生育
    0.42
     سلا
    0.42
     slov
    0.42
     provenant
    0.41
    駐車
    0.40
    시스템
    0.40
    ัง
    0.39
    オー
    0.39
    Aster
    0.39
    POSITIVE LOGITS
    きたいと思います
    0.44
     Bulldog
    0.42
     компанию
    0.40
     shaken
    0.40
     drugs
    0.40
     besieged
    0.40
     manh
    0.39
     speedily
    0.39
     stony
    0.39
     adopted
    0.39
    Act Density 0.014%

    No Known Activations