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

    Neuronpedia

    INDEX
    Explanations

    instances of programming constructs and syntax elements

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

    Equals signs and parentheses

    np_acts-logits-general · gemini-2.0-flash

    method definitions like `SetLabel`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.94
    IntoConstraints
    -0.73
     <=",
    -0.70
    Démographie
    -0.69
    Obrázky
    -0.68
     PublicKey
    -0.66
    sizeCache
    -0.65
     onAnimation
    -0.64
    KommentareTeilen
    -0.64
    IUrlHelper
    -0.64
    POSITIVE LOGITS
     تانيه
    0.59
    ٍ
    0.58
    din
    0.45
    inoma
    0.44
     Pressing
    0.43
    ֵי
    0.43
    psin
    0.43
    beb
    0.43
     anzu
    0.43
    drink
    0.43
    Act Density 0.031%

    No Known Activations