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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hy
    -0.07
    mj
    -0.07
    Tk
    -0.06
    (ev
    -0.06
    mediately
    -0.06
     TextArea
    -0.06
    \xd
    -0.06
    yclic
    -0.06
    (xy
    -0.06
    (idx
    -0.06
    POSITIVE LOGITS
     erre
    0.07
    /Documents
    0.07
     Tolkien
    0.06
     جریان
    0.06
     murdering
    0.06
     discounts
    0.06
    /star
    0.06
    .tif
    0.06
    hair
    0.06
    _BLE
    0.06
    Act Density 0.002%

    No Known Activations