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

    Neuronpedia

    INDEX
    Explanations

    references and citations in a document

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

    code or configuration files

    np_acts-logits-general · gemini-2.0-flash

    reference and program/results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.45
     تضيفلها
    -0.41
    GenerationType
    -0.40
    큼
    -0.40
     forState
    -0.40
    rowsiness
    -0.39
    Ӕ
    -0.39
    componentWill
    -0.38
    ysql
    -0.38
    RectangleBorder
    -0.37
    POSITIVE LOGITS
     reference
    2.88
     Reference
    2.66
    reference
    2.58
    Reference
    2.50
     REFERENCE
    2.44
     references
    2.33
     References
    2.06
    REFERENCE
    2.06
     referencia
    2.00
     référence
    2.00
    Act Density 0.490%

    No Known Activations