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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sudoku
    -0.08
     thief
    -0.07
     Weiss
    -0.07
     dood
    -0.07
     couch
    -0.06
    .tiles
    -0.06
     lush
    -0.06
     dancing
    -0.06
    美食
    -0.06
     ambassador
    -0.06
    POSITIVE LOGITS
    彷
    0.07
     Sebast
    0.07
     RT
    0.07
    -------------</
    0.07
     Marketable
    0.07
     //--------------------------------
    0.07
    铸
    0.07
     γ
    0.07
     et
    0.07
    历年
    0.07
    Act Density 0.053%

    No Known Activations