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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     analy
    -0.07
    minster
    -0.06
    巻
    -0.06
    SharedPtr
    -0.06
    Enlarge
    -0.06
    축
    -0.06
    STAT
    -0.06
    _RING
    -0.06
    Pix
    -0.06
    imestep
    -0.06
    POSITIVE LOGITS
    istant
    0.07
     après
    0.07
    τες
    0.06
     thick
    0.06
    gil
    0.06
     гре
    0.06
    panse
    0.06
     ort
    0.06
    obl
    0.06
     قدم
    0.06
    Act Density 0.009%

    No Known Activations