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

    Neuronpedia

    INDEX
    Explanations

    phrases that provide disclaimers or additional context

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

    providing context or side notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pflichten
    -0.44
     gemens
    -0.43
     pouvoit
    -0.42
     avoient
    -0.42
     feroit
    -0.42
     kurtka
    -0.41
     betweenstory
    -0.40
    området
    -0.40
     quæ
    -0.40
     szczeg
    -0.39
    POSITIVE LOGITS
    FWIW
    0.72
     FYI
    0.68
    FYI
    0.66
    brigens
    0.66
    Билгалдахарш
    0.52
     btw
    0.52
    лтамалар
    0.48
    一応
    0.48
     BTW
    0.47
     الرياضيه
    0.46
    Act Density 0.023%

    No Known Activations