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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fuzzy
    -0.07
    Ip
    -0.07
    误
    -0.07
     Istanbul
    -0.06
    .year
    -0.06
     num
    -0.06
     hym
    -0.06
     farms
    -0.06
    .mod
    -0.06
     земли
    -0.06
    POSITIVE LOGITS
    lake
    0.06
    迪
    0.06
    ransition
    0.06
     раза
    0.06
    .Mobile
    0.06
     unnatural
    0.06
    iệ
    0.06
    宽
    0.06
     सज
    0.05
    _aes
    0.05
    Act Density 0.001%

    No Known Activations