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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diana
    -0.06
    'Re
    -0.06
    onica
    -0.06
     Flash
    -0.06
    Backup
    -0.06
     Hunger
    -0.06
    Ž
    -0.06
     "[
    -0.06
    的地
    -0.06
    Flash
    -0.06
    POSITIVE LOGITS
    dued
    0.07
    	yield
    0.07
     vay
    0.07
     yeast
    0.07
     reducing
    0.06
     withholding
    0.06
     kingdoms
    0.06
     Spotlight
    0.06
    �
    0.06
    {↵
    0.06
    Act Density 0.020%

    No Known Activations