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

    Neuronpedia

    INDEX
    Explanations

    terms related to direct references or assertions

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

    direct link

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ทรง
    -0.38
    地说道
    -0.38
     now
    -0.37
     Internasional
    -0.37
     Gottes
    -0.37
    typeparam
    -0.35
     chaud
    -0.34
     maintenant
    -0.34
     bây
    -0.33
     courant
    -0.32
    POSITIVE LOGITS
    WebElementEntity
    0.84
    LookAnd
    0.80
    0.75
     estekak
    0.69
     nahilalakip
    0.68
    хьтан
    0.68
    twimg
    0.67
     ivelany
    0.66
     queſta
    0.66
    WriteTagHelper
    0.64
    Act Density 0.001%

    No Known Activations