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

    Neuronpedia

    INDEX
    Explanations

    specific characters and symbols used in code or markup formats

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

    code and math syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defStyleAttr
    -0.37
     estekak
    -0.37
     resourceCulture
    -0.37
    PageRoute
    -0.36
     defStyle
    -0.36
    PerformLayout
    -0.34
     ویکی‌پدیا
    -0.34
     RouterModule
    -0.33
    ModelAdmin
    -0.33
    archiviato
    -0.31
    POSITIVE LOGITS
    0.61
    DockStyle
    0.56
    CodeAttribute
    0.49
     useState
    0.49
    lotl
    0.49
     Geſch
    0.48
    +#+
    0.48
    KommentareTeilen
    0.47
    AddTagHelper
    0.46
    ambo
    0.45
    Act Density 0.014%

    No Known Activations