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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Media
    -0.07
    crit
    -0.07
    _algo
    -0.07
     cup
    -0.07
     Obst
    -0.06
    endencies
    -0.06
    vida
    -0.06
     EMP
    -0.06
     ostr
    -0.06
     ห
    -0.06
    POSITIVE LOGITS
    (svg
    0.07
     української
    0.06
    卒
    0.06
    :before
    0.06
    iệt
    0.06
     双线
    0.06
    ][_
    0.06
     trồng
    0.06
    ايش
    0.06
    schemas
    0.06
    Act Density 0.020%

    No Known Activations