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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity, explanation, or contextual information

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

    simplicity or obviousness

    np_acts-logits-general · gemini-2.0-flash

    straightforward, simple, obvious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.58
    Билгалдахарш
    -0.43
    eleste
    -0.43
    Atsauces
    -0.42
    AlterField
    -0.40
    ="@+
    -0.39
    Παραπομπές
    -0.38
     informée
    -0.38
    最快更新
    -0.38
    Converters
    -0.38
    POSITIVE LOGITS
     straightforward
    0.57
     obvious
    0.56
    obvious
    0.53
    obviously
    0.50
     obviously
    0.49
     simple
    0.48
    mTitle
    0.47
     literally
    0.47
     AssemblyTitle
    0.46
    単純
    0.45
    Act Density 0.276%

    No Known Activations