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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     соответств
    -0.07
    ewis
    -0.07
    Sortable
    -0.06
     وي
    -0.06
    ैश
    -0.06
    -Co
    -0.06
    idor
    -0.06
    \Client
    -0.06
    نامج
    -0.06
     Fukushima
    -0.06
    POSITIVE LOGITS
     expended
    0.07
     Ihren
    0.07
    (anchor
    0.06
    ghest
    0.06
     Qualcomm
    0.06
     NotificationCenter
    0.06
     تحلیل
    0.06
     그녀의
    0.06
     مدينة
    0.06
    (ALOAD
    0.06
    Act Density 0.001%

    No Known Activations