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

    Neuronpedia

    INDEX
    Explanations

    names of people and their associations in academic or professional contexts

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

    authors and co-authors of papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
    RegressionTest
    -0.69
    
    -0.56
    ftagPool
    -0.53
    PostInfinity
    -0.53
     itſelf
    -0.50
    Hentet
    -0.49
     itself
    -0.48
    原始内容存档于
    -0.47
    featureID
    -0.46
    POSITIVE LOGITS
     Advisors
    0.40
    참고
    0.39
     counsels
    0.37
    Authors
    0.37
     Directors
    0.37
    rinology
    0.36
    (&:
    0.36
     Royale
    0.36
     advisors
    0.35
     Assigned
    0.35
    Act Density 0.263%

    No Known Activations