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

    Neuronpedia

    INDEX
    Explanations

    clauses that provide additional information or context about a subject

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

    specifies properties or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.48
    gal
    -0.43
     Democ
    -0.41
    بوابة
    -0.41
    omyia
    -0.41
     BAT
    -0.40
    Hymen
    -0.39
     TANG
    -0.39
     جام
    -0.39
    +#+#
    -0.38
    POSITIVE LOGITS
     seragam
    0.48
    rungsseite
    0.48
    SharedCtor
    0.48
     setempat
    0.43
     TAMBÉM
    0.43
     Kelurahan
    0.43
     argint
    0.43
    CloseOperation
    0.43
     Infórmanos
    0.42
    ⓧ
    0.41
    Act Density 0.197%

    No Known Activations