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
     прот
    -0.07
     azure
    -0.06
    売
    -0.06
     Tolkien
    -0.06
    乱
    -0.06
     Mr
    -0.06
     unrecognized
    -0.06
     coated
    -0.06
    .renderer
    -0.06
     zatím
    -0.06
    POSITIVE LOGITS
     компании
    0.07
     juni
    0.07
     contract
    0.07
     menstr
    0.06
    _FILENAME
    0.06
    の大
    0.06
    政策
    0.06
     Spanish
    0.06
    ()",
    0.06
    _Callback
    0.06
    Act Density 0.012%

    No Known Activations