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

    Neuronpedia

    INDEX
    Explanations

    Software tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deborah
    -0.06
     undertake
    -0.06
     Hydro
    -0.06
    imizer
    -0.06
    ley
    -0.06
     나는
    -0.06
    eneration
    -0.06
     pushing
    -0.06
     textiles
    -0.06
     ########################################################################
    -0.06
    POSITIVE LOGITS
    ITEM
    0.08
     úkol
    0.07
     fost
    0.06
    .lab
    0.06
    .failed
    0.06
    �
    0.06
     achter
    0.06
    .literal
    0.06
     Spinner
    0.06
    	window
    0.06
    Act Density 0.062%

    No Known Activations