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

    Neuronpedia

    INDEX
    Explanations

    -Type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _manual
    -0.07
    말
    -0.07
     若要
    -0.06
    ToStr
    -0.06
     correl
    -0.06
     꼭
    -0.06
     hoops
    -0.06
    EXPECTED
    -0.06
    ovit
    -0.06
     BT
    -0.06
    POSITIVE LOGITS
    -Type
    0.07
     الشركة
    0.07
     رقم
    0.07
    _Collections
    0.06
    	LOG
    0.06
    ��
    0.06
    	throws
    0.06
     sacrific
    0.06
     monks
    0.06
     Ø
    0.06
    Act Density 0.001%

    No Known Activations