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

    Neuronpedia

    INDEX
    Explanations

    terms related to scholarly publications

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

    published evaluations and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ณี
    -0.48
     jeito
    -0.48
    eway
    -0.47
    QMetaType
    -0.47
     razie
    -0.47
     gimana
    -0.46
     wektor
    -0.45
     bezpieczeństwa
    -0.44
    Personendaten
    -0.44
    setMode
    -0.43
    POSITIVE LOGITS
     published
    1.83
    published
    1.64
     publish
    1.61
     Published
    1.55
    Published
    1.48
     Publish
    1.44
     publishes
    1.37
    publish
    1.34
     publishing
    1.30
     PUBLISHED
    1.30
    Act Density 0.015%

    No Known Activations