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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to roughness or irregularity in objects or textures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    rugged, robust, sturdy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.63
     goldfish
    -0.52
    泉
    -0.50
    MessageOf
    -0.50
    
    -0.49
    NameInMap
    -0.49
     Dalai
    -0.49
    点此举报
    -0.48
     JpaRepository
    -0.48
    queryInterface
    -0.47
    POSITIVE LOGITS
     rugged
    1.95
     Rugged
    1.81
    Rug
    1.23
     robuste
    0.90
     Rugg
    0.90
     Rug
    0.81
    robust
    0.80
     sturdy
    0.79
    Robust
    0.78
     robust
    0.76
    Act Density 0.001%

    No Known Activations