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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Summit
    -0.09
    (fd
    -0.08
     fd
    -0.08
     porto
    -0.08
     gas
    -0.07
     engineers
    -0.07
     mosa
    -0.07
    .Utility
    -0.07
     Gas
    -0.07
     summit
    -0.07
    POSITIVE LOGITS
     Vietnamese
    0.10
    Vietnam
    0.09
     김
    0.09
     Punjabi
    0.08
     होंगे
    0.08
     zult
    0.08
    São
    0.08
     ہوگا
    0.08
    ประเทศไทย
    0.08
     Korean
    0.08
    Act Density 0.005%

    No Known Activations