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

    Neuronpedia

    INDEX
    Explanations

    graduated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     storia
    -0.07
     愛
    -0.06
    Sets
    -0.06
     Reich
    -0.06
     shape
    -0.06
    inker
    -0.06
    Ste
    -0.06
     corner
    -0.06
     owe
    -0.06
     bidding
    -0.06
    POSITIVE LOGITS
     graduated
    0.11
     graduating
    0.09
     Awake
    0.08
     egreg
    0.07
     graduation
    0.07
    ducted
    0.07
     Advances
    0.07
    탈
    0.07
    mour
    0.07
    *↵
    0.07
    Act Density 0.010%

    No Known Activations