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

    Neuronpedia

    INDEX
    Explanations

    any of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फ्रॉम
    0.46
    放下
    0.44
     литературы
    0.43
     от
    0.42
     souff
    0.42
     nonstop
    0.42
    דר
    0.41
     refills
    0.40
     tex
    0.40
     cooks
    0.39
    POSITIVE LOGITS
    들에게
    0.48
    ل
    0.44
     표현
    0.43
    에게
    0.43
    anud
    0.42
    esinde
    0.40
     écailles
    0.40
     Geschenk
    0.39
    عبير
    0.39
     부분
    0.38
    Act Density 0.001%

    No Known Activations