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

    Neuronpedia

    INDEX
    Explanations

    decisions and comments

    np_max-act · gemini-2.0-flash

    This neuron detects nouns denoting official actions or statements (e.g., “announcement,” “decision,” “comments”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    your
    -0.06
    óc
    -0.06
     Caroline
    -0.06
    ANDROID
    -0.06
    Overrides
    -0.06
    Project
    -0.06
    наруж
    -0.06
     μην
    -0.05
    .libs
    -0.05
     وفق
    -0.05
    POSITIVE LOGITS
     fragmentation
    0.06
    _TRUE
    0.06
    [element
    0.06
     dime
    0.06
     Tud
    0.06
     Initialization
    0.06
    선거
    0.06
     Discuss
    0.06
     συμπ
    0.06
     representatives
    0.06
    Act Density 0.057%

    No Known Activations