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

    Neuronpedia

    INDEX
    Explanations

    structure or format indicators in text

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

    Code or numbers within text

    np_acts-logits-general · gemini-2.0-flash

    mathematical product notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.62
     مواليد
    -0.60
    ädie
    -0.57
    Referanser
    -0.56
    openConnection
    -0.55
    värr
    -0.52
     potrivit
    -0.50
    MethodManager
    -0.50
    LabelTagHelper
    -0.50
     окна
    -0.50
    POSITIVE LOGITS
    __*/
    0.63
    ivil
    0.62
    anthus
    0.60
    __(/*!
    0.56
    </tbody>
    0.54
     EconPapers
    0.54
    bior
    0.53
    #
    0.53
    \}_{
    0.53
    enumii
    0.52
    Act Density 0.537%

    No Known Activations