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

    Neuronpedia

    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anzi
    -0.08
     due
    -0.07
     quanto
    -0.07
    Arg
    -0.07
    本站
    -0.07
    iev
    -0.07
    AlmostEqual
    -0.07
    .Wh
    -0.07
    Packet
    -0.07
    .urlopen
    -0.07
    POSITIVE LOGITS
    yards
    0.08
    */↵↵↵
    0.07
     אוהבים
    0.07
     SMART
    0.07
    _gift
    0.07
    啃
    0.07
     york
    0.07
     Scan
    0.07
     Keys
    0.07
    ôtel
    0.07
    Act Density 0.024%

    No Known Activations