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

    Neuronpedia

    INDEX
    Explanations

    closing quotation marks or other closing brackets in a document

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

    numerical data presented in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    `
    -0.26
    ener
    -0.23
    tig
    -0.23
     Sal
    -0.22
    fil
    -0.21
    k
    -0.21
    pu
    -0.20
    Sal
    -0.20
    ab
    -0.20
    θυ
    -0.20
    POSITIVE LOGITS
    tagHelperRunner
    1.09
     Roskov
    0.90
     defaultstate
    0.87
    Personendaten
    0.86
     nakalista
    0.84
     للمعارف
    0.82
     メンテナ
    0.79
     パンチラ
    0.78
    <unused16>
    0.77
    <unused17>
    0.77
    Act Density 0.005%

    No Known Activations