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

    Neuronpedia

    INDEX
    Explanations

    sugar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    炉
    -0.07
    	Y
    -0.07
     بم
    -0.07
     عرب
    -0.07
     Yours
    -0.06
     share
    -0.06
    xEE
    -0.06
     Ά
    -0.06
    إنجليزية
    -0.06
     Salman
    -0.06
    POSITIVE LOGITS
    プロ
    0.07
    exion
    0.07
     REF
    0.06
    �
    0.06
    uetype
    0.06
    	false
    0.06
    extended
    0.06
    osto
    0.06
    แค
    0.06
    mmm
    0.06
    Act Density 0.003%

    No Known Activations