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

    Neuronpedia

    INDEX
    Explanations

    low

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тоб
    -0.07
     Truly
    -0.06
    %"),↵
    -0.06
     UBND
    -0.06
    nest
    -0.06
    oppers
    -0.06
    -mult
    -0.06
    	Map
    -0.06
     더욱
    -0.06
    京都
    -0.06
    POSITIVE LOGITS
     hesap
    0.08
     privileges
    0.07
    واع
    0.06
     यह
    0.06
    シー
    0.06
     手机
    0.06
     improbable
    0.06
     Shaft
    0.06
     inconvenient
    0.06
     MOM
    0.06
    Act Density 0.072%

    No Known Activations