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

    Neuronpedia

    INDEX
    Explanations

    hasOwnProperty (in code)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parfait
    -0.08
    _rating
    -0.08
    -taking
    -0.07
    ਦਾ
    -0.07
     générale
    -0.07
    йте
    -0.07
     nightclub
    -0.07
    दा
    -0.07
    inger
    -0.07
    roat
    -0.07
    POSITIVE LOGITS
     માલ
    0.08
    enuine
    0.08
     contaminants
    0.08
     Kunststoff
    0.08
    ueblos
    0.08
     Conc
    0.08
     awaken
    0.08
     Alle
    0.08
    .pipeline
    0.08
     pipelines
    0.08
    Act Density 0.001%

    No Known Activations