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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exporters
    -0.07
     thự
    -0.07
    一批
    -0.07
    血脂
    -0.07
    使之
    -0.07
    洽谈
    -0.06
    emia
    -0.06
     pago
    -0.06
    对标
    -0.06
    =Value
    -0.06
    POSITIVE LOGITS
     RootState
    0.08
     Shake
    0.07
    Whatever
    0.07
     Hot
    0.07
    innerHTML
    0.06
     unterstützt
    0.06
    erving
    0.06
     whole
    0.06
    ряд
    0.06
    不满意
    0.06
    Act Density 0.005%

    No Known Activations