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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

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

    numerical and algebraic calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Krakowie
    -0.42
    zyż
    -0.37
    )++;
    -0.36
    wapV
    -0.36
     Puedes
    -0.35
    abbix
    -0.34
    thumbsup
    -0.33
     gerichtet
    -0.33
     exacting
    -0.33
     extraordinarily
    -0.33
    POSITIVE LOGITS
    XmlAccessType
    0.50
    AddTagHelper
    0.50
    AndEndTag
    0.50
     ModelExpression
    0.45
     AKS
    0.45
    RegressionTest
    0.43
    活躍
    0.43
    :✨
    0.43
    \{\\
    0.42
    楔
    0.42
    Act Density 0.020%

    No Known Activations