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

    Neuronpedia

    INDEX
    Explanations

    structural elements of code, particularly control flow constructs and brackets

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    old English script or code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.51
     AspNetCore
    -0.48
    anelli
    -0.48
    jek
    -0.46
    _^
    -0.45
    //
    -0.45
    ø
    -0.43
     كومونز
    -0.43
    orn
    -0.41
     dover
    -0.41
    POSITIVE LOGITS
     BoxFit
    0.78
     kasarigan
    0.75
    neſs
    0.75
    ſelf
    0.73
     Jefus
    0.66
     preſent
    0.65
    🏻‍♀️
    0.65
     itſelf
    0.64
     ſtate
    0.63
     unſ
    0.63
    Act Density 0.279%

    No Known Activations