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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessing
    -0.08
    مدير
    -0.07
    	dispatch
    -0.07
    -President
    -0.07
    langle
    -0.07
    ﲇ
    -0.07
     dump
    -0.07
    .resolve
    -0.07
     LIN
    -0.07
    Dean
    -0.07
    POSITIVE LOGITS
     Sms
    0.07
    יצו
    0.07
     מבלי
    0.07
    抗生素
    0.07
     كال
    0.06
    字体
    0.06
    봇
    0.06
     Ikea
    0.06
    .other
    0.06
    ߖ
    0.06
    Act Density 0.001%

    No Known Activations