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

    Neuronpedia

    INDEX
    Explanations

    rankings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    陇
    -0.08
    ormal
    -0.07
    crm
    -0.07
    inv
    -0.07
    百姓
    -0.07
    coop
    -0.07
    Brandon
    -0.06
    рай
    -0.06
    Items
    -0.06
     indispens
    -0.06
    POSITIVE LOGITS
     ser
    0.07
    른
    0.07
    ência
    0.07
     가능성
    0.06
    两人
    0.06
    	CString
    0.06
    اوية
    0.06
    德国
    0.06
     Divider
    0.06
     Venezuelan
    0.06
    Act Density 0.017%

    No Known Activations