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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remorse
    -0.07
    ＿
    -0.06
    warts
    -0.06
     운
    -0.06
     sezon
    -0.06
    _hosts
    -0.06
    ons
    -0.06
    guided
    -0.06
    ‏
    -0.06
    етом
    -0.06
    POSITIVE LOGITS
     Information
    0.07
     klein
    0.07
    contact
    0.07
     бер
    0.06
     linewidth
    0.06
     nail
    0.06
    оск
    0.06
    <class
    0.06
    rank
    0.06
    _almost
    0.06
    Act Density 0.001%

    No Known Activations