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

    Neuronpedia

    INDEX
    Explanations

    interrupts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anese
    0.38
    lectual
    0.38
    ebut
    0.37
    竻
    0.37
    parentNode
    0.37
    den
    0.37
    angle
    0.37
    ian
    0.36
    oplan
    0.36
    ly
    0.36
    POSITIVE LOGITS
     discontinuities
    0.50
     প্রাণের
    0.50
     interrupts
    0.50
    Interruptions
    0.49
     चौटाला
    0.48
     interruptions
    0.46
     breakfasts
    0.44
     formules
    0.43
     interrupt
    0.41
     prefabricated
    0.41
    Act Density 0.000%

    No Known Activations