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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     energia
    -0.07
     iPhone
    -0.06
    wendung
    -0.06
     Cons
    -0.06
     sailors
    -0.06
     rooftop
    -0.06
     ByteArray
    -0.06
    _ad
    -0.06
    madığı
    -0.06
    bias
    -0.06
    POSITIVE LOGITS
     unpack
    0.07
    (instance
    0.07
    üy
    0.07
    	category
    0.06
    amment
    0.06
    ()?>
    0.06
    (sockfd
    0.06
    <span
    0.06
     twilight
    0.06
     LARGE
    0.06
    Act Density 0.009%

    No Known Activations