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

    Neuronpedia

    INDEX
    Explanations

    byte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    字符
    -0.07
    Scripts
    -0.06
    Items
    -0.06
     nearer
    -0.06
    _COLOR
    -0.06
    illin
    -0.06
    uve
    -0.06
     Shah
    -0.06
    کور
    -0.06
     ور
    -0.06
    POSITIVE LOGITS
     صن
    0.07
     spou
    0.07
     EC
    0.06
    feedback
    0.06
    NotSupportedException
    0.06
     EntryPoint
    0.06
     电
    0.06
     dev
    0.06
     treasury
    0.06
     đưa
    0.06
    Act Density 0.002%

    No Known Activations