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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successive
    -0.08
     Panama
    -0.07
     neat
    -0.07
    熊
    -0.07
    (para
    -0.07
     inert
    -0.07
     متح
    -0.07
    ests
    -0.07
     Sheikh
    -0.07
    :set
    -0.07
    POSITIVE LOGITS
    uppy
    0.06
    alsa
    0.06
    上的
    0.06
     آنلاین
    0.06
     ||
↵
    0.06
     detailing
    0.06
    _support
    0.06
     spolu
    0.06
     Б
    0.05
     "");
↵
    0.05
    Act Density 0.079%

    No Known Activations