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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foolish
    -0.08
    -flag
    -0.07
    _most
    -0.07
    <this
    -0.07
     Goose
    -0.07
    הצעה
    -0.07
    触摸
    -0.07
    头脑
    -0.07
    .Port
    -0.07
    סדר
    -0.07
    POSITIVE LOGITS
    0.07
    .Blue
    0.07
    TEM
    0.07
    .logout
    0.07
     ETA
    0.06
     Greenland
    0.06
    ko
    0.06
    ]];↵
    0.06
    EB
    0.06
    Clinical
    0.06
    Act Density 0.007%

    No Known Activations