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

    Neuronpedia

    INDEX
    Explanations

    references to evidence and examples in discussions or arguments

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

    providing citations and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.46
     kaarangay
    -0.42
    seamnă
    -0.40
     ویکی‌پدیا
    -0.38
     welkom
    -0.38
    舺
    -0.37
    ClCompile
    -0.37
     olympique
    -0.36
     régionale
    -0.35
    AddTagHelper
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.59
     examples
    0.56
     Cite
    0.50
     esempi
    0.49
    examples
    0.49
     Beispiele
    0.47
     cite
    0.47
     ejemplos
    0.46
     Examples
    0.45
     exemples
    0.45
    Act Density 0.337%

    No Known Activations