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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    general
    -0.07
    indir
    -0.07
     customary
    -0.07
    (btn
    -0.07
     mechanically
    -0.07
    imary
    -0.06
    收益
    -0.06
     Motors
    -0.06
     expedition
    -0.06
    (prog
    -0.06
    POSITIVE LOGITS
     соедин
    0.07
     постеп
    0.06
    -num
    0.06
     секрет
    0.06
     PCI
    0.06
     {}\
    0.06
    )])↵↵
    0.06
    erno
    0.06
    HTTPHeader
    0.06
    Eff
    0.06
    Act Density 0.012%

    No Known Activations