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

    Neuronpedia

    INDEX
    Explanations

    procedure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MAX
    -0.07
    notin
    -0.06
    Nat
    -0.06
     WORLD
    -0.06
    ang
    -0.06
    ognition
    -0.06
    ots
    -0.06
     king
    -0.06
     King
    -0.06
    ling
    -0.06
    POSITIVE LOGITS
    Procedure
    0.10
     procedures
    0.10
     procedure
    0.08
     traged
    0.08
     Beverage
    0.08
     Procedure
    0.08
    078
    0.08
     thủ
    0.08
    повід
    0.08
    ظر
    0.07
    Act Density 0.016%

    No Known Activations