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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    measure
    -0.07
    cout
    -0.06
     місця
    -0.06
    .colors
    -0.06
    erge
    -0.06
     Spark
    -0.06
    _)
    -0.06
     Hastings
    -0.06
     Appeals
    -0.06
    cba
    -0.06
    POSITIVE LOGITS
    zeit
    0.07
    dük
    0.06
    -dimensional
    0.06
    _packages
    0.06
     NotImplemented
    0.06
    -offs
    0.06
    ynom
    0.06
    击
    0.06
    /platform
    0.06
    дром
    0.06
    Act Density 0.136%

    No Known Activations