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

    Neuronpedia

    INDEX
    Explanations

    plers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    markup
    -0.07
    _Profile
    -0.06
    ┴
    -0.06
    Revision
    -0.06
     قتل
    -0.06
     tribunal
    -0.06
    Receive
    -0.05
     rửa
    -0.05
     رز
    -0.05
    figures
    -0.05
    POSITIVE LOGITS
    ---↵↵
    0.07
     Влади
    0.07
    )\
    0.07
     ++$
    0.07
     |↵↵
    0.07
    Metro
    0.07
     colossal
    0.06
     Cameron
    0.06
     Mohammed
    0.06
    坡
    0.06
    Act Density 0.490%

    No Known Activations