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

    Neuronpedia

    INDEX
    Explanations

    types and variables related to programming and data structures

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

    template code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мәкал
    -0.56
    apimachinery
    -0.54
    étoit
    -0.54
    protoimpl
    -0.53
     mijne
    -0.53
     pleaſure
    -0.51
     zijne
    -0.48
     Wikiseite
    -0.47
     enfans
    -0.47
    OGND
    -0.47
    POSITIVE LOGITS
    ↵
    0.57
    ↵↵
    0.53
    ↵↵↵↵
    0.52
     Lul
    0.50
     beb
    0.50
     Munk
    0.48
    endregion
    0.48
    ivore
    0.48
    ↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵
    0.48
    Act Density 0.049%

    No Known Activations