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

    Neuronpedia

    INDEX
    Explanations

    upon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -
    -0.08
     דולר
    -0.08
     Nolan
    -0.08
    🥥
    -0.07
     sentence
    -0.07
    湖南
    -0.07
    
    -0.07
     Exercise
    -0.07
    <
    -0.07
    腰
    -0.07
    POSITIVE LOGITS
     the
    0.08
     ",";↵
    0.07
     upon
    0.07
    .articles
    0.06
    >());↵↵
    0.06
    ierge
    0.06
    ܚ
    0.06
     ([]
    0.06
    勃
    0.06
    ᵏ
    0.06
    Act Density 0.019%

    No Known Activations