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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lul
    -0.07
     hatte
    -0.07
     휴
    -0.06
    road
    -0.06
     timings
    -0.06
     Tess
    -0.06
    BD
    -0.06
     располож
    -0.06
     Rif
    -0.06
    距離
    -0.06
    POSITIVE LOGITS
    就会
    0.07
     можна
    0.07
    加工
    0.07
     ”
    0.06
     waypoints
    0.06
    '];↵↵
    0.06
    ��️
    0.06
    樣
    0.06
    Modern
    0.06
     ble
    0.06
    Act Density 0.087%

    No Known Activations