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

    Neuronpedia

    INDEX
    Explanations

    underscore characters indicating variable naming conventions in code

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

    ABS date format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heritage
    -0.37
     cherchez
    -0.35
    Heritage
    -0.34
    EmailAddress
    -0.34
    Harry
    -0.33
     nationwide
    -0.33
    removeItem
    -0.33
     HI
    -0.33
     Reason
    -0.32
    Ill
    -0.32
    POSITIVE LOGITS
    dtos
    0.69
     незавершена
    0.65
    StoryboardSegue
    0.63
     jScrollPane
    0.61
     DTO
    0.59
    tvguidetime
    0.58
    parsedMessage
    0.58
    DTOs
    0.58
     dto
    0.55
    localctx
    0.54
    Act Density 0.001%

    No Known Activations