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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ltra
    -0.07
    aza
    -0.07
    _Y
    -0.07
    Luc
    -0.07
     المؤ
    -0.07
    gments
    -0.07
    _cat
    -0.07
    紙
    -0.07
    Pont
    -0.06
    pone
    -0.06
    POSITIVE LOGITS
     burnt
    0.07
    (sid
    0.07
     yoktur
    0.06
    荷
    0.06
     Direction
    0.06
     Started
    0.06
    费
    0.06
     Saw
    0.06
     Here
    0.06
    -that
    0.06
    Act Density 0.010%

    No Known Activations