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

    Neuronpedia

    INDEX
    Explanations

    Economic dates and months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iter
    -0.08
    VILLE
    -0.08
    _Call
    -0.07
    Creates
    -0.07
     demos
    -0.07
     uncomfort
    -0.07
    .Per
    -0.07
    _side
    -0.07
    施行
    -0.07
    Surv
    -0.06
    POSITIVE LOGITS
    ropped
    0.07
     opened
    0.07
     McGu
    0.07
    топ
    0.07
     lib
    0.07
    我爸
    0.07
    量产
    0.06
    打破
    0.06
    荞
    0.06
     KA
    0.06
    Act Density 0.003%

    No Known Activations