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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soda
    -0.08
    ルド
    -0.07
     jak
    -0.07
     Abuse
    -0.06
    Merc
    -0.06
     Betting
    -0.06
     Wong
    -0.06
     Sachs
    -0.06
     laut
    -0.06
     thrive
    -0.06
    POSITIVE LOGITS
    PEAR
    0.07
    供
    0.07
    oust
    0.07
     yayınlan
    0.07
    (atom
    0.07
    FB
    0.06
    (Database
    0.06
    깠
    0.06
     remained
    0.06
    でしょうね
    0.06
    Act Density 0.002%

    No Known Activations