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

    Neuronpedia

    INDEX
    Explanations

    spying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _legacy
    -0.07
    .secondary
    -0.07
    縣
    -0.06
    배
    -0.06
     managers
    -0.06
     classes
    -0.06
    insky
    -0.06
     McCl
    -0.06
     khẳng
    -0.06
    서
    -0.06
    POSITIVE LOGITS
     ez
    0.08
     az
    0.07
     por
    0.07
     itemList
    0.07
     bum
    0.07
     nghỉ
    0.07
     هزینه
    0.06
     Brooklyn
    0.06
     compassionate
    0.06
    oggled
    0.06
    Act Density 0.007%

    No Known Activations