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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and interactions in various contexts

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

    immediately preceding specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    prepositions and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Obrázky
    -0.57
    ChildScrollView
    -0.55
    ########.
    -0.54
    XmlAccessType
    -0.54
     ModelExpression
    -0.52
     שוליים
    -0.49
    ***********/
    -0.47
    *************/
    -0.47
    ➌
    -0.47
    ReusableCell
    -0.47
    POSITIVE LOGITS
    unhofer
    0.40
    ched
    0.36
    vasti
    0.34
    bis
    0.32
     тем
    0.31
     sami
    0.31
    ftagPool
    0.30
    nologue
    0.30
    che
    0.30
    storm
    0.30
    Act Density 2.124%

    No Known Activations