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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and their collaborations in scientific literature

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

    Names followed by a capitalized last name initial

    np_acts-logits-general · gemini-2.0-flash

    names paired with "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Perfor
    -0.49
     Quicks
    -0.48
     Noct
    -0.48
     Diagonal
    -0.47
     Hyster
    -0.46
     Apri
    -0.46
     Discrimin
    -0.45
     Circum
    -0.44
     Antic
    -0.44
     Pum
    -0.44
    POSITIVE LOGITS
    oa̍t
    0.64
     propOrder
    0.63
     Chwiliwch
    0.62
    Personensuche
    0.60
     الرياضيه
    0.59
    expandindo
    0.59
     صوتيه
    0.56
     ModelExpression
    0.55
     république
    0.55
    ьаж
    0.55
    Act Density 1.554%

    No Known Activations