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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling opinions or reflections on personal experiences

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

    legal and explanatory context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.63
     صوتيه
    -0.59
     EconPapers
    -0.59
    majánló
    -0.59
     ویکی‌پدی
    -0.57
    IndentedString
    -0.56
    ImageContext
    -0.56
     doInBackground
    -0.55
    :✨
    -0.55
    utilisons
    -0.54
    POSITIVE LOGITS
     kæ
    0.41
    krim
    0.32
     اله
    0.32
    xsi
    0.32
     order
    0.31
     Hess
    0.30
     condemn
    0.30
    eux
    0.30
     religione
    0.30
     vermelha
    0.29
    Act Density 0.662%

    No Known Activations