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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects the formal discourse markers of academic papers—words like “We,” “Our,” “The,” “goal,” and “in this setting” that introduce problem statements, assumptions, and main contributions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     đứng
    -0.07
    fait
    -0.07
    ADB
    -0.06
    Tx
    -0.06
    flash
    -0.06
    อร
    -0.06
    dv
    -0.06
    .put
    -0.06
     이러
    -0.06
    "]],↵
    -0.06
    POSITIVE LOGITS
     podnik
    0.07
    _sex
    0.06
     versatility
    0.06
     мужчин
    0.06
    _parser
    0.06
    ной
    0.06
     ihrer
    0.06
     Project
    0.06
    .squeeze
    0.06
    (dir
    0.06
    Act Density 0.019%

    No Known Activations