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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polym
    -0.07
    として
    -0.07
     television
    -0.07
     Mong
    -0.07
     tp
    -0.06
     designation
    -0.06
    iterations
    -0.06
    _bin
    -0.06
    bios
    -0.06
     مسائل
    -0.06
    POSITIVE LOGITS
    主任
    0.07
    ISON
    0.06
    :SetPoint
    0.06
     -------
    0.06
    .bean
    0.06
    .strategy
    0.06
    :\/\/
    0.06
     Ivan
    0.06
    "]↵
    0.06
    ison
    0.06
    Act Density 0.058%

    No Known Activations