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

    Neuronpedia

    INDEX
    Explanations

    studs and walls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     설명
    -0.07
     darker
    -0.07
     Player
    -0.07
     practise
    -0.07
     vám
    -0.07
    (player
    -0.06
    _op
    -0.06
     Latest
    -0.06
    ehicle
    -0.06
    La
    -0.06
    POSITIVE LOGITS
    _##
    0.07
    	ft
    0.06
     cush
    0.06
    <Character
    0.06
    .RelativeLayout
    0.06
     siege
    0.06
    др
    0.06
     HACK
    0.06
     KY
    0.06
    PURE
    0.05
    Act Density 0.011%

    No Known Activations