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

    Neuronpedia

    INDEX
    Explanations

    data table

    np_max-act · gemini-2.0-flash

    The neuron activates on technical-attribute labels or field names (e.g. “Engine,” “Release Date,” “Max Power,” “무게,” “원산지”) in specs-style tables.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    roveň
    -0.07
     `[
    -0.06
    ávání
    -0.06
    Hand
    -0.06
    ernational
    -0.06
     Dh
    -0.06
     IK
    -0.06
    Yeah
    -0.06
     Myth
    -0.06
     USER
    -0.06
    POSITIVE LOGITS
    .pageSize
    0.07
    /authentication
    0.07
     thẻ
    0.07
    _mappings
    0.07
    {},
    0.06
     �
    0.06
     (++
    0.06
    레
    0.06
    )./
    0.06
    ョ
    0.06
    Act Density 0.079%

    No Known Activations