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

    Neuronpedia

    INDEX
    Explanations

    elements related to purchasing or acquiring written work or articles online

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

    preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.68
     تضيفلها
    -0.66
    WriteBarrier
    -0.66
    ViewImports
    -0.65
     بيها
    -0.62
    GraphicsUnit
    -0.62
     שוליים
    -0.60
    RegistryLite
    -0.59
    PyExc
    -0.58
    inerja
    -0.58
    POSITIVE LOGITS
    RTLI
    0.60
     Pind
    0.51
     PARSER
    0.47
    untung
    0.46
    mıştır
    0.45
    aturing
    0.44
    FUNC
    0.43
    ционное
    0.43
    ıyoruz
    0.43
    galus
    0.42
    Act Density 0.099%

    No Known Activations