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

    Neuronpedia

    INDEX
    Explanations

    references to statistical analysis and parameters

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

    Comes after the word "the"

    np_acts-logits-general · gemini-2.0-flash

    explaining a reason or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قيقي
    -0.57
     vecchia
    -0.55
     principaux
    -0.54
     vrais
    -0.53
     officielles
    -0.53
    adə
    -0.51
     Lieblings
    -0.50
     irgende
    -0.49
    essentiel
    -0.48
    Reco
    -0.47
    POSITIVE LOGITS
     fact
    1.11
     lack
    1.07
     Tatsache
    0.96
     sheer
    0.95
    fact
    0.90
     extensive
    0.87
     high
    0.84
    lack
    0.83
     huge
    0.83
    huge
    0.81
    Act Density 0.610%

    No Known Activations