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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iciel
    -0.07
    -election
    -0.07
     Caesar
    -0.06
    	sd
    -0.06
     legality
    -0.06
     uncomfort
    -0.06
     Controllers
    -0.06
    .Arg
    -0.06
     enrollment
    -0.06
    	bus
    -0.06
    POSITIVE LOGITS
     useNewUrlParser
    0.07
     inbox
    0.06
    青
    0.06
    toInt
    0.06
    ’e
    0.06
    �장
    0.06
    BUTTONDOWN
    0.06
     اله
    0.06
    HTML
    0.06
    ЙЙ
    0.06
    Act Density 0.053%

    No Known Activations