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

    Neuronpedia

    INDEX
    Explanations

    Z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lowercase
    -0.08
    ຄ
    -0.08
    enumerate
    -0.08
    upal
    -0.08
    ivating
    -0.07
    แฟ
    -0.07
    ليم
    -0.07
     nước
    -0.07
    Ἦ
    -0.07
    .rec
    -0.07
    POSITIVE LOGITS
     Exterior
    0.07
    )>↵
    0.07
    깄
    0.07
    -X
    0.07
    >');↵↵
    0.07
    masters
    0.07
    	sleep
    0.06
     Auschwitz
    0.06
     Kauf
    0.06
    		↵
    0.06
    Act Density 0.019%

    No Known Activations