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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tournament
    -0.07
     wood
    -0.06
    yii
    -0.06
    _body
    -0.06
    HttpException
    -0.06
     CommandLine
    -0.06
     Oscars
    -0.06
     Performance
    -0.06
    tagName
    -0.06
     datetime
    -0.06
    POSITIVE LOGITS
    τας
    0.07
    edd
    0.07
    ；
    0.06
    グ
    0.06
     hj
    0.06
    。</
    0.06
    ？
    0.06
    ıyorum
    0.06
    ="'
    0.06
    ='')↵
    0.06
    Act Density 0.005%

    No Known Activations