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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity and straightforwardness in understanding or discussing concepts

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

    simplicity or obviousness

    np_acts-logits-general · gemini-2.0-flash

    simple straightforward clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueGeneration
    -0.48
    Personendaten
    -0.45
    참고
    -0.44
    Izvori
    -0.44
    Билгалдахарш
    -0.40
     GenerationType
    -0.39
     bağlantılar
    -0.38
    Παραπομπές
    -0.37
    лтамалар
    -0.36
     Jezus
    -0.36
    POSITIVE LOGITS
    tagHelper
    0.52
     propOrder
    0.50
    inheritDoc
    0.46
    TRAILING
    0.45
    WebVitals
    0.43
     cjs
    0.43
     obvious
    0.42
     clear
    0.42
     Vikipedi
    0.41
     clara
    0.40
    Act Density 0.367%

    No Known Activations