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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly focusing on identifiers or counts

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

    numbers in math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Desa
    -0.41
     Suomessa
    -0.35
    娘娘
    -0.34
     nombreuses
    -0.34
     possible
    -0.34
     Dosen
    -0.34
     Freih
    -0.34
     Gallery
    -0.34
     Thirty
    -0.33
    Possible
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.80
    RenderAtEndOf
    0.73
    AddTagHelper
    0.73
    tagHelperRunner
    0.68
    yntaxException
    0.66
    ContentLoaded
    0.65
     CreateTagHelper
    0.65
    Diweddarwch
    0.64
    DockStyle
    0.64
    +#+#
    0.64
    Act Density 0.044%

    No Known Activations