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

    Neuronpedia

    INDEX
    Explanations

    web development

    np_max-act · gemini-2.0-flash

    meta-instructional directives about how to perform or format a task (e.g., requests to search, generate, or follow a specified response format).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ande
    -0.06
    _ord
    -0.06
     trace
    -0.06
    omba
    -0.06
    constexpr
    -0.06
    真正
    -0.06
     vul
    -0.06
    _clr
    -0.06
    shader
    -0.06
    UMB
    -0.06
    POSITIVE LOGITS
    ông
    0.07
    оу
    0.07
     accus
    0.07
     még
    0.07
    sın
    0.07
     florida
    0.07
    uplicate
    0.06
     Nevertheless
    0.06
    nin
    0.06
    setData
    0.06
    Act Density 0.481%

    No Known Activations