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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Secondly
    -0.07
    的隱私權
    -0.07
    	push
    -0.07
    mäßig
    -0.07
     mainly
    -0.07
     Cuba
    -0.07
    啰
    -0.07
     Scroll
    -0.07
     Vill
    -0.07
    	min
    -0.07
    POSITIVE LOGITS
    TECT
    0.07
    ^.
    0.07
    球星
    0.07
    ڄ
    0.06
     Wide
    0.06
    乡村
    0.06
    人民
    0.06
    .FromResult
    0.06
    atest
    0.06
     יום
    0.06
    Act Density 0.002%

    No Known Activations