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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components and their properties

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

    Code, data, names, and values

    np_acts-logits-general · gemini-2.0-flash

    assignments and equality checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.75
     يتيمه
    -0.69
    OGND
    -0.65
    rrggbb
    -0.64
     ويكيميديا
    -0.62
    aderie
    -0.60
     Forder
    -0.60
    olymer
    -0.60
    Vidite
    -0.59
    ########.
    -0.59
    POSITIVE LOGITS
     =
    1.28
     ==
    0.79
    return
    0.77
     ===
    0.64
     =>
    0.63
     -
    0.62
     !=
    0.62
     :
    0.61
     –
    0.58
     said
    0.57
    Act Density 0.227%

    No Known Activations