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

    Neuronpedia

    INDEX
    Explanations

    code elements and keywords related to data management and operations

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

    code structure and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.93
     Administrativna
    -0.92
     queſta
    -0.90
    -0.88
     betweenstory
    -0.85
     Perſ
    -0.85
    ThroughAttribute
    -0.85
    TagMode
    -0.84
     ModelExpression
    -0.84
    ſelf
    -0.82
    POSITIVE LOGITS
    3
    0.50
    1
    0.47
    2
    0.47
     
    0.47
    7
    0.44
    4
    0.44
    0
    0.43
    5
    0.43
    8
    0.41
    9
    0.40
    Act Density 0.005%

    No Known Activations