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

    Neuronpedia

    INDEX
    Explanations

    specific names, terms, and keywords related to academic or scientific contexts

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

    Cogna lords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.52
    ✨:
    -0.50
    SBATCH
    -0.47
    fjspx
    -0.47
    ⓧ
    -0.46
     Grüsse
    -0.45
     onlyOwner
    -0.45
    RunWith
    -0.45
    Děkuji
    -0.45
    Deletes
    -0.44
    POSITIVE LOGITS
    合
    0.39
    account
    0.39
     VIDEOT
    0.39
    フライ
    0.36
     taco
    0.35
     syke
    0.35
     <<<<<<<<<<<<<<
    0.34
    لار
    0.34
    ///<
    0.34
     LAL
    0.34
    Act Density 0.991%

    No Known Activations