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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotes

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

    user input parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    -0.34
     off
    -0.29
     here
    -0.29
     close
    -0.29
     in
    -0.28
    breadcrumb
    -0.28
    ly
    -0.28
     geldi
    -0.28
     Gay
    -0.28
     from
    -0.28
    POSITIVE LOGITS
    ftagPool
    0.84
    AndEndTag
    0.82
     propOrder
    0.79
    IUrlHelper
    0.77
    +#+#
    0.75
    InjectAttribute
    0.72
     lenker
    0.71
    rrggbb
    0.70
    IndentedString
    0.70
     فريبيس
    0.69
    Act Density 0.016%

    No Known Activations