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

    Neuronpedia

    INDEX
    Explanations

    Code testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '.',
    -0.06
    shows
    -0.06
     Zn
    -0.06
    <d
    -0.06
     yup
    -0.06
     Ordered
    -0.06
    Gs
    -0.06
     přičemž
    -0.06
     crafted
    -0.06
    opped
    -0.06
    POSITIVE LOGITS
     ellipse
    0.07
    忆
    0.07
    戶
    0.06
     yoktur
    0.06
    岗位
    0.06
    ่วน
    0.06
    ATURE
    0.06
    unexpected
    0.06
    ทร
    0.06
    واع
    0.06
    Act Density 0.001%

    No Known Activations