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
    Beam
    -0.06
    "H
    -0.06
     newX
    -0.06
    48
    -0.06
    _INIT
    -0.06
    #$
    -0.06
     voi
    -0.06
     ż
    -0.06
    ennis
    -0.06
     гри
    -0.06
    POSITIVE LOGITS
    _monitor
    0.08
     dbl
    0.07
    .concurrent
    0.07
     Cardinals
    0.07
     rootView
    0.06
    -lat
    0.06
    ignal
    0.06
    twenty
    0.06
    	describe
    0.06
     listings
    0.06
    Act Density 0.005%

    No Known Activations