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

    Neuronpedia

    INDEX
    Explanations

    questions formatted with a "Q" prefix, indicating inquiry or requests for information

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

    Q: question marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.29
    PERATURE
    -0.23
     conciencia
    -0.21
    axios
    -0.21
     suspended
    -0.20
    ablemente
    -0.20
     attack
    -0.20
     apla
    -0.20
     rappeler
    -0.20
     never
    -0.19
    POSITIVE LOGITS
    Q
    1.38
     Q
    1.16
    httphttps
    0.93
    ########.
    0.93
    帖最后由
    0.90
    Ｑ
    0.88
    Personendaten
    0.88
    WriteTagHelper
    0.88
    TagMode
    0.83
    ConstraintMaker
    0.82
    Act Density 0.002%

    No Known Activations