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

    Neuronpedia

    INDEX
    Explanations

    Change in quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	List
    -0.06
    cash
    -0.06
    Hugh
    -0.06
     directions
    -0.06
     Qui
    -0.06
     cref
    -0.06
    alleries
    -0.06
    한테
    -0.06
    alamat
    -0.06
     Gonz
    -0.06
    POSITIVE LOGITS
    _FOCUS
    0.07
    .chart
    0.07
     Suppose
    0.07
     enthusiastically
    0.07
    ुद
    0.06
    <header
    0.06
     bug
    0.06
    .Alpha
    0.06
     Beard
    0.06
     Από
    0.06
    Act Density 0.015%

    No Known Activations