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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and voting-related terms

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

    votes and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.60
    TypedDataSet
    -0.57
    ViewInit
    -0.56
     poveznice
    -0.54
     desmotivaciones
    -0.53
     queſta
    -0.53
     дописавши
    -0.52
    endgroup
    -0.52
     Bewußt
    -0.52
    Portail
    -0.51
    POSITIVE LOGITS
     minority
    0.43
    scrapy
    0.41
     majority
    0.41
     Minority
    0.40
     conservative
    0.37
    FailureListener
    0.37
     vote
    0.36
     Democratic
    0.36
     ارت
    0.35
    Autoritní
    0.35
    Act Density 0.010%

    No Known Activations