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

    Neuronpedia

    INDEX
    Explanations

    keys and values in structured data formats

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

    defining variable types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.89
     Савезне
    -0.70
     queſta
    -0.69
    MessageOf
    -0.60
    windowFixed
    -0.59
    setVerticalGroup
    -0.56
     linkovi
    -0.56
    ⓧ
    -0.55
    étoit
    -0.55
    Gweler
    -0.55
    POSITIVE LOGITS
     type
    0.68
     Type
    0.62
    type
    0.60
    getType
    0.56
     TYPE
    0.56
    Type
    0.56
    TYPE
    0.54
    setType
    0.53
     tipo
    0.53
    xtype
    0.50
    Act Density 0.053%

    No Known Activations