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

    Neuronpedia

    INDEX
    Explanations

    html <head> tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAC
    -0.07
    _BASIC
    -0.06
     peas
    -0.06
    ----</
    -0.06
     한국
    -0.06
     Tow
    -0.06
    턱
    -0.06
    -cont
    -0.06
    防范
    -0.06
    排队
    -0.06
    POSITIVE LOGITS
    -reviewed
    0.07
    férence
    0.07
    Honestly
    0.07
    畋
    0.07
    でしたが
    0.06
    _unique
    0.06
    .buffer
    0.06
    езультат
    0.06
    如果你
    0.06
    พวกเขา
    0.06
    Act Density 0.002%

    No Known Activations