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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, ingredients, or instructions in recipes or processes

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

    references and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chapters
    -0.35
     chapter
    -0.31
    chapters
    -0.30
     transport
    -0.29
     tölt
    -0.28
     TRANSPORT
    -0.27
     tyd
    -0.27
    TRANSPORT
    -0.27
    orrho
    -0.27
    Transport
    -0.26
    POSITIVE LOGITS
     BoxFit
    0.65
    <?
    0.62
    delwed
    0.60
    ########.
    0.59
    :✨
    0.59
    UrlResolution
    0.59
    دانشنامهٔ
    0.58
    EndContext
    0.58
    queryInterface
    0.57
     שוליים
    0.56
    Act Density 0.202%

    No Known Activations