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

    Neuronpedia

    INDEX
    Explanations

    beyond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المنطقة
    -0.07
    epad
    -0.07
     Defines
    -0.07
     adultos
    -0.07
     como
    -0.07
    =len
    -0.06
    こん
    -0.06
    -common
    -0.06
     آقای
    -0.06
     cố
    -0.06
    POSITIVE LOGITS
    ئ
    0.07
     unlikely
    0.06
    /ml
    0.06
    SKTOP
    0.06
     McMaster
    0.06
     晴
    0.06
    Ac
    0.06
    corner
    0.06
    اهر
    0.06
     polygon
    0.06
    Act Density 0.002%

    No Known Activations