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

    Neuronpedia

    INDEX
    Explanations

    references to legal circumstances and relationships

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

    after baseline / met / trit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.55
    ſelves
    -0.54
     ſy
    -0.53
     OFDb
    -0.52
     تضيفلها
    -0.51
     fubject
    -0.50
    HasAnnotation
    -0.47
     itſelf
    -0.47
    andExpect
    -0.47
     AssemblyCompany
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.40
    áctenos
    0.39
    optionalTypeArgs
    0.39
     مشين
    0.39
    posables
    0.39
     bienvenida
    0.38
    сылкі
    0.38
    tagext
    0.35
     disposição
    0.35
     stipulated
    0.35
    Act Density 0.098%

    No Known Activations