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
    Driving
    -0.07
    ableView
    -0.06
    误
    -0.06
    ."),
    -0.06
     accreditation
    -0.06
     Governments
    -0.06
     MotionEvent
    -0.06
     panels
    -0.06
     EK
    -0.06
     vốn
    -0.06
    POSITIVE LOGITS
    	y
    0.06
    skip
    0.06
     잠
    0.06
     sam
    0.06
     slog
    0.06
    .writeInt
    0.06
     mamma
    0.06
    alph
    0.06
     정말
    0.06
    __((
    0.06
    Act Density 0.000%

    No Known Activations