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

    Neuronpedia

    INDEX
    Explanations

    class/function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     given
    0.43
    的问题
    0.43
    给定
    0.42
     réelle
    0.40
     Given
    0.40
    Given
    0.40
     Docker
    0.39
     enumeration
    0.39
     문제는
    0.39
     probleme
    0.39
    POSITIVE LOGITS
    funct
    0.43
    lsulfanyl
    0.38
     संशोधित
    0.36
    ಂಕ್
    0.36
    Plaintiffs
    0.35
    birthday
    0.35
    getRow
    0.35
    addChild
    0.35
    diving
    0.34
     जीता
    0.34
    Act Density 0.002%

    No Known Activations