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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns

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

    your noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.34
     murió
    -0.33
     calentamiento
    -0.33
     vyš
    -0.32
     juzgar
    -0.31
     murieron
    -0.31
     passieren
    -0.30
    ้งาน
    -0.30
     muere
    -0.30
     пришел
    -0.30
    POSITIVE LOGITS
    TagMode
    0.67
    __*/
    0.66
    #+#
    0.57
     CURIAM
    0.56
    ScopeManager
    0.55
     kasarigan
    0.53
    kuuta
    0.53
    WebElementEntity
    0.52
    ParallelGroup
    0.52
    AddTagHelper
    0.50
    Act Density 0.208%

    No Known Activations