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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defamation
    -0.06
    Ά
    -0.06
     Adler
    -0.06
    Locations
    -0.06
    colm
    -0.06
     Mart
    -0.06
     locker
    -0.06
     Cookbook
    -0.06
     ulus
    -0.06
    _PERMISSION
    -0.06
    POSITIVE LOGITS
     začal
    0.07
    っていた
    0.06
    _vid
    0.06
     gpu
    0.06
    	pw
    0.06
     associative
    0.06
    /*----------------------------------------------------------------
    0.06
    ł
    0.06
    UP
    0.06
     빨
    0.06
    Act Density 0.000%

    No Known Activations