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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical proofs and logical conclusions

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

    Followed by adverbs of time or manner

    np_acts-logits-general · gemini-2.0-flash

    We now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.44
    :✨
    -0.40
    GEBURTSDATUM
    -0.38
     Hoje
    -0.38
    UnknownFieldSet
    -0.37
    ᅟ
    -0.37
    -0.36
    nvarchar
    -0.35
    expandindo
    -0.34
    ➟
    -0.34
    POSITIVE LOGITS
     now
    1.94
    Now
    1.69
     Now
    1.63
     ahora
    1.52
     теперь
    1.47
     maintenant
    1.46
    Теперь
    1.45
    now
    1.43
    Ahora
    1.33
     Теперь
    1.28
    Act Density 1.079%

    No Known Activations