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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .doc
    -0.08
     convex
    -0.08
    鲂
    -0.07
     tex
    -0.07
    成语
    -0.07
    .Caption
    -0.07
    高效
    -0.07
     embarked
    -0.07
    Reach
    -0.07
     -->
↵
↵
    -0.07
    POSITIVE LOGITS
    不管你
    0.08
    أوضاع
    0.07
    아버지
    0.07
    (identifier
    0.06
    pare
    0.06
     bands
    0.06
     cage
    0.06
    شاه
    0.06
    权利
    0.06
    現場
    0.06
    Act Density 0.046%

    No Known Activations