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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Writer
    -0.07
     sig
    -0.06
     팬
    -0.06
     electronically
    -0.06
    .Base
    -0.06
     druhé
    -0.06
     each
    -0.06
    _dir
    -0.06
    scan
    -0.06
    scenes
    -0.06
    POSITIVE LOGITS
     declaring
    0.07
     possibly
    0.06
    -CN
    0.06
     też
    0.06
     Had
    0.06
     tends
    0.06
    	dfs
    0.06
     отвер
    0.06
    扎
    0.06
     touched
    0.06
    Act Density 0.058%

    No Known Activations