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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     custody
    -0.07
     province
    -0.07
    -members
    -0.07
    (names
    -0.06
     addresses
    -0.06
     Window
    -0.06
     windows
    -0.06
    Generated
    -0.06
     Allows
    -0.06
    离
    -0.06
    POSITIVE LOGITS
    _COLS
    0.07
    کم
    0.07
    -Б
    0.06
    ég
    0.06
    este
    0.06
    $list
    0.06
    进
    0.06
     şöyle
    0.06
    ฟอร
    0.06
     birinin
    0.06
    Act Density 0.093%

    No Known Activations