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

    Neuronpedia

    INDEX
    Explanations

    era

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HAVE
    -0.08
     woods
    -0.07
     Soup
    -0.07
    口罩
    -0.07
     garner
    -0.07
    .pe
    -0.07
    装置
    -0.07
     Funds
    -0.07
     compounds
    -0.07
     cloak
    -0.07
    POSITIVE LOGITS
    른
    0.07
    딛
    0.06
    뎟
    0.06
    펍
    0.06
    擊
    0.06
    לר
    0.06
    	input
    0.06
    слав
    0.06
     IDirect
    0.06
    ᠷ
    0.06
    Act Density 0.010%

    No Known Activations