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

    Neuronpedia

    INDEX
    Explanations

    system calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Roy
    -0.07
    rah
    -0.06
    วย
    -0.06
    lients
    -0.06
     vil
    -0.06
     ด
    -0.06
     comer
    -0.06
    664
    -0.06
    ula
    -0.06
    má
    -0.06
    POSITIVE LOGITS
    leading
    0.06
     اسر
    0.06
    _ARROW
    0.06
     mnie
    0.06
     flyer
    0.06
     Placement
    0.06
     обыч
    0.06
    	pw
    0.06
     машин
    0.06
     Submit
    0.06
    Act Density 0.001%

    No Known Activations