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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knives
    -0.07
     piş
    -0.06
    wi
    -0.06
     OAuth
    -0.06
    _CAR
    -0.06
    Regular
    -0.06
     Rub
    -0.06
     Bas
    -0.06
     perse
    -0.06
     Tus
    -0.06
    POSITIVE LOGITS
    ertos
    0.08
    3
    0.07
     fasta
    0.07
    ordable
    0.07
    webView
    0.07
    4
    0.07
    -condition
    0.07
    2
    0.07
     مات
    0.07
     článku
    0.06
    Act Density 0.006%

    No Known Activations