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

    Neuronpedia

    INDEX
    Explanations

    non-maximum suppression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invoices
    0.38
     diplomas
    0.37
     inaccuracy
    0.37
    ुलिस
    0.36
    also
    0.36
    Screenshot
    0.36
    modifiers
    0.36
    udders
    0.36
    Upon
    0.36
     bandages
    0.35
    POSITIVE LOGITS
     non
    1.13
     Non
    1.05
    Non
    0.93
    non
    0.93
     NON
    0.92
     नॉन
    0.86
    非
    0.80
    NON
    0.78
     गैर
    0.74
     非
    0.72
    Act Density 0.035%

    No Known Activations