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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KE
    -0.06
     QUE
    -0.06
     Pu
    -0.06
    죄
    -0.06
    Pu
    -0.05
     Cannes
    -0.05
    _PUT
    -0.05
     нату
    -0.05
    catid
    -0.05
    Canvas
    -0.05
    POSITIVE LOGITS
     gan
    0.07
     diagnostic
    0.07
    _elem
    0.07
    심
    0.06
    elem
    0.06
    	ad
    0.06
    (dat
    0.06
     jest
    0.06
     expert
    0.06
     sloppy
    0.06
    Act Density 0.010%

    No Known Activations