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

    Neuronpedia

    INDEX
    Explanations

    exchange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    993
    -0.06
    (array
    -0.06
    943
    -0.06
    InMillis
    -0.06
    yı
    -0.06
    cookie
    -0.06
    333
    -0.06
    :>
    -0.06
     antioxidants
    -0.06
    ひと
    -0.06
    POSITIVE LOGITS
    Unlock
    0.07
    	copy
    0.06
    Für
    0.06
     چت
    0.06
    ؤال
    0.06
     condolences
    0.06
    िम
    0.06
     дра
    0.06
    issement
    0.06
    Він
    0.06
    Act Density 0.004%

    No Known Activations