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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     has
    -0.07
     OpenSSL
    -0.06
     is
    -0.06
    _comp
    -0.06
     isr
    -0.06
    	Y
    -0.06
     Sullivan
    -0.06
    Davis
    -0.06
     درآمد
    -0.06
     Doch
    -0.06
    POSITIVE LOGITS
     cross
    0.08
     -----↵
    0.07
    reten
    0.06
    .cross
    0.06
    зація
    0.06
    อง
    0.06
    ‌م
    0.06
    _HOME
    0.06
     mission
    0.06
     görün
    0.06
    Act Density 0.192%

    No Known Activations