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

    Neuronpedia

    INDEX
    Explanations

    Arabic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -training
    -0.07
    support
    -0.07
     museums
    -0.06
     develops
    -0.06
     съ
    -0.06
    Feed
    -0.06
    ูตร
    -0.06
    �
    -0.06
     Morrison
    -0.06
     Opcode
    -0.06
    POSITIVE LOGITS
     الش
    0.09
     الق
    0.09
     الك
    0.09
     الب
    0.08
     الخ
    0.08
     الع
    0.08
     للأ
    0.08
    الأ
    0.08
     الد
    0.08
     الإ
    0.08
    Act Density 0.015%

    No Known Activations