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
    ---@
    -0.07
     Boston
    -0.07
     מת
    -0.07
     clen
    -0.06
     tán
    -0.06
     DATE
    -0.06
    tx
    -0.06
     >↵
    -0.06
    dcc
    -0.06
     Yay
    -0.06
    POSITIVE LOGITS
    -human
    0.08
    繁
    0.07
     hust
    0.07
     Knife
    0.07
     harvesting
    0.06
    研究人员
    0.06
    śli
    0.06
    ,s
    0.06
    _exempt
    0.06
     Sink
    0.06
    Act Density 0.037%

    No Known Activations