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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and expressions

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

    mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.80
    parsedMessage
    -0.75
    pingente
    -0.74
     zoude
    -0.71
    ThroughAttribute
    -0.71
    rawDesc
    -0.69
    mpagne
    -0.69
    arangay
    -0.66
     مشين
    -0.64
     Waray
    -0.64
    POSITIVE LOGITS
    From
    0.42
    You
    0.37
    hline
    0.34
    0.34
    They
    0.33
    Using
    0.33
    GroupLayout
    0.33
    ≦)
    0.33
    Before
    0.31
    Between
    0.31
    Act Density 0.006%

    No Known Activations