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

    Neuronpedia

    INDEX
    Explanations

    declarations and definitions of datasets and their attributes in programming contexts

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

    Tokens indicating data characteristics

    np_acts-logits-general · gemini-2.0-flash

    Tag names and data fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.52
    XtraReports
    -0.47
    }();
    -0.46
    نامج
    -0.45
    GEBURTS
    -0.44
     tortuga
    -0.44
    Begriffsklä
    -0.43
    +#+#
    -0.43
     converge
    -0.43
    ArrowToggle
    -0.42
    POSITIVE LOGITS
     Timestamp
    0.70
     timestamp
    0.61
     timestamps
    0.60
     anthrop
    0.58
     Metadata
    0.58
    anskje
    0.57
    Unnamed
    0.56
    PhysRevD
    0.56
    HttpHeaders
    0.56
     betweenstory
    0.55
    Act Density 0.358%

    No Known Activations