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

    Neuronpedia

    INDEX
    Explanations

    refuse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐍
    -0.07
    	Mat
    -0.07
    털
    -0.07
    dish
    -0.07
     التواصل
    -0.06
    섹
    -0.06
    具有
    -0.06
     nữ
    -0.06
    �
    -0.06
    上の
    -0.06
    POSITIVE LOGITS
    巡察
    0.07
     glob
    0.07
    (video
    0.07
    רוס
    0.07
     escalating
    0.07
    גה
    0.06
    urchases
    0.06
    一般是
    0.06
     Vance
    0.06
     Baker
    0.06
    Act Density 0.008%

    No Known Activations