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

    Neuronpedia

    INDEX
    Explanations

    references to authors or creators of works

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

    by author name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.57
     estekak
    -0.54
     chrétienne
    -0.50
    الإنجليزية
    -0.49
     operaciones
    -0.48
     aikaa
    -0.45
     całym
    -0.44
     operativos
    -0.43
     personalidad
    -0.43
     skolan
    -0.42
    POSITIVE LOGITS
    ⓧ
    0.56
     by
    0.56
     作者
    0.53
    ❋
    0.50
     BY
    0.50
     AUTHOR
    0.50
    
    0.48
    by
    0.47
     karya
    0.47
     author
    0.46
    Act Density 0.107%

    No Known Activations