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

    Neuronpedia

    INDEX
    Explanations

    Advertisements

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric metadata—counts, dates, edition numbers, view or rating figures, and similar statistical or numeric details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uição
    -0.07
     utilizes
    -0.07
    INY
    -0.07
    FIT
    -0.07
    Degree
    -0.07
     creek
    -0.07
    CENTER
    -0.06
    Seat
    -0.06
     网
    -0.06
    atrix
    -0.06
    POSITIVE LOGITS
    antt
    0.06
    ？
    0.06
    .subscriptions
    0.06
     створю
    0.06
     나타
    0.06
    �
    0.06
     vmin
    0.06
    LinearLayout
    0.06
     cons
    0.06
     Nicolas
    0.06
    Act Density 0.004%

    No Known Activations