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

    Neuronpedia

    INDEX
    Explanations

    argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    チェ
    -0.07
    ização
    -0.07
    י
    -0.07
     pandemic
    -0.06
     tutte
    -0.06
    bedPane
    -0.06
     witches
    -0.06
     sans
    -0.06
     Крім
    -0.06
    40
    -0.06
    POSITIVE LOGITS
     arguments
    0.08
     argument
    0.08
    .ArgumentParser
    0.08
     이야기
    0.08
     arg
    0.08
     args
    0.08
    	arg
    0.07
    μα
    0.07
     Demir
    0.07
    ?????
    0.07
    Act Density 0.036%

    No Known Activations