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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    郑
    -0.06
    eydi
    -0.06
    、“
    -0.06
    AMESPACE
    -0.06
     브
    -0.06
     amor
    -0.06
    柄
    -0.06
    注意
    -0.06
    地址
    -0.06
    _VLAN
    -0.06
    POSITIVE LOGITS
    elles
    0.07
    -color
    0.07
    AsStream
    0.06
    going
    0.06
     تلك
    0.06
     Eden
    0.06
     Border
    0.06
    ales
    0.06
    bose
    0.06
    lej
    0.06
    Act Density 0.012%

    No Known Activations