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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hon
    -0.07
    Tracking
    -0.07
     Conf
    -0.06
     בנוג
    -0.06
    منع
    -0.06
    Portable
    -0.06
    蹢
    -0.06
     Canadians
    -0.06
    mdp
    -0.06
     Miner
    -0.06
    POSITIVE LOGITS
     URL
    0.08
     prio
    0.08
     прод
    0.08
     категории
    0.08
     עריכה
    0.07
    dojo
    0.07
     мяс
    0.07
     информацию
    0.07
     xlabel
    0.07
    ":"","
    0.07
    Act Density 0.002%

    No Known Activations