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

    Neuronpedia

    INDEX
    Explanations

    class or id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    客
    -0.07
    яз
    -0.06
    VP
    -0.06
    IMATE
    -0.06
    ".$
    -0.06
    vp
    -0.06
     Slots
    -0.06
    割
    -0.06
     });
    -0.06
     polar
    -0.06
    POSITIVE LOGITS
    dük
    0.07
     듯
    0.06
    -issue
    0.06
    /s
    0.06
    0.06
     misdemean
    0.06
    	sizeof
    0.06
    apgolly
    0.06
     lepší
    0.06
    StartupScript
    0.06
    Act Density 0.014%

    No Known Activations