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

    Neuronpedia

    INDEX
    Explanations

    information and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    revalidator
    0.46
     बिकॉज
    0.46
    enumValues
    0.45
    वर्ष
    0.42
     rodr
    0.41
    沃尔
    0.40
     前回
    0.40
    lüssel
    0.39
    ㄵ
    0.39
    Rodr
    0.39
    POSITIVE LOGITS
    Site
    0.41
     SOURCE
    0.40
    Source
    0.39
     induced
    0.39
     Source
    0.38
    [
    0.37
     SVG
    0.37
     SITE
    0.37
    ART
    0.37
     Ê
    0.36
    Act Density 0.000%

    No Known Activations