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

    Neuronpedia

    INDEX
    Explanations

    injection/XSS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    низ
    -0.07
     velice
    -0.06
     chia
    -0.06
    자가
    -0.06
    caret
    -0.06
    _bw
    -0.06
     shortly
    -0.06
    _ALLOC
    -0.06
    αιο
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     JSONException
    0.07
     Trit
    0.06
     Zach
    0.06
     Views
    0.06
    ngoing
    0.06
     Did
    0.06
    ようです
    0.06
    「……
    0.06
     Tear
    0.06
     Дон
    0.06
    Act Density 0.026%

    No Known Activations