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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ax
    -0.07
     Him
    -0.07
     tres
    -0.07
    /tos
    -0.06
    λλά
    -0.06
     gint
    -0.06
    urgent
    -0.06
    (pkt
    -0.06
     +'
    -0.06
    Seg
    -0.06
    POSITIVE LOGITS
    管
    0.07
     spawned
    0.07
    서는
    0.07
     handwriting
    0.06
     应
    0.06
    .Rendering
    0.06
    			↵
    0.06
    [^
    0.06
     modelling
    0.06
     plumber
    0.06
    Act Density 0.031%

    No Known Activations