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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不安
    -0.07
     (!$
    -0.06
    ウス
    -0.06
     destinations
    -0.06
     accusations
    -0.06
    остью
    -0.06
    	append
    -0.06
    yc
    -0.06
     ضمن
    -0.06
    ¨ط
    -0.05
    POSITIVE LOGITS
     Springer
    0.07
     DM
    0.07
     Cooking
    0.07
     Madrid
    0.07
     Stephens
    0.07
     Working
    0.07
    (hw
    0.06
     "-";↵
    0.06
    ==↵
    0.06
     الحي
    0.06
    Act Density 0.001%

    No Known Activations