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

    Neuronpedia

    INDEX
    Explanations

    try

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric literals (integer and floating‐point constants) in the source.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    etailed
    -0.07
    ematic
    -0.06
    _irq
    -0.06
    ening
    -0.06
    eus
    -0.06
    herence
    -0.06
    Eta
    -0.06
    |$
    -0.06
     состояния
    -0.06
     Pattern
    -0.06
    POSITIVE LOGITS
     inviting
    0.07
    ython
    0.06
     asking
    0.06
    รอง
    0.06
    (item
    0.06
    soup
    0.06
    iec
    0.06
    .Tasks
    0.06
     самой
    0.06
     dryer
    0.06
    Act Density 0.009%

    No Known Activations