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

    Neuronpedia

    INDEX
    Explanations

    relationships between entities and their attributes or qualities

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

    conjunctions in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.61
     Paglinawan
    -0.60
     للمعارف
    -0.60
    featureID
    -0.59
    hyrchwyd
    -0.57
    нгред
    -0.57
    rrggbb
    -0.56
    AnchorTagHelper
    -0.56
    kháu
    -0.56
     surla
    -0.54
    POSITIVE LOGITS
    me
    0.32
    rste
    0.30
     particular
    0.30
     particularly
    0.29
     great
    0.28
     roh
    0.28
     حض
    0.28
    ticularly
    0.27
    istik
    0.27
    adan
    0.27
    Act Density 0.428%

    No Known Activations