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

    Neuronpedia

    INDEX
    Explanations

    _irq

    np_max-act · gemini-2.0-flash

    This neuron detects low-level kernel synchronization calls (e.g. spin_lock_irq_save / spin_unlock_irq_restore).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    onaut
    -0.06
     repeated
    -0.06
    细
    -0.06
     arrog
    -0.06
    描述
    -0.06
    Foot
    -0.06
     독
    -0.06
     пон
    -0.06
    .b
    -0.06
    '";
↵
    -0.06
    POSITIVE LOGITS
    _irq
    0.08
     ACPI
    0.07
     Seiten
    0.06
     typeId
    0.06
     midterm
    0.06
    frican
    0.06
    _IRQn
    0.06
    prove
    0.06
    ionate
    0.06
     Ґ
    0.06
    Act Density 0.000%

    No Known Activations