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

    Neuronpedia

    INDEX
    Explanations

    references to publications and legal districts or divisions

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

    United States District Courts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.45
     Identität
    -0.44
     étoient
    -0.44
     hutan
    -0.43
     rumput
    -0.43
     héroe
    -0.41
     feroit
    -0.40
     cristiana
    -0.40
     laaj
    -0.40
     beras
    -0.40
    POSITIVE LOGITS
     ANGELES
    1.05
     ويكيپيديا
    0.98
     Nast
    0.63
    0.60
    INCREMENT
    0.59
    -------------</
    0.58
    GEBURTSDATUM
    0.57
    InputModule
    0.50
    født
    0.50
     للاسماء
    0.50
    Act Density 0.006%

    No Known Activations