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

    Neuronpedia

    INDEX
    Explanations

    terms related to internal and external characteristics or conditions

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

    Appears before non-English text or code

    np_acts-logits-general · gemini-2.0-flash

    3 Theorem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GRANTED
    -0.60
    énario
    -0.59
     Winaray
    -0.59
     LoggerFactory
    -0.54
     Вікі
    -0.51
    RuleContext
    -0.50
     pinulongan
    -0.49
    GIVEREF
    -0.48
     Kohn
    -0.48
    kloped
    -0.47
    POSITIVE LOGITS
     démar
    0.60
     dépens
    0.54
    ⓧ
    0.52
     fédé
    0.51
     témo
    0.50
    PERATURE
    0.48
    romole
    0.48
     terjadinya
    0.47
     pregi
    0.46
    bilirsiniz
    0.46
    Act Density 0.091%

    No Known Activations