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

    Neuronpedia

    INDEX
    Explanations

    percentiles and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    吆
    -0.07
     tug
    -0.07
     exceeding
    -0.07
    ]],
    -0.07
     >>↵↵
    -0.07
    /////////////////////////////////////////////////////////////////////////////↵
    -0.07
     CAPITAL
    -0.07
     lobbying
    -0.07
     towering
    -0.07
     aby
    -0.07
    POSITIVE LOGITS
    ieve
    0.07
    antt
    0.07
    captures
    0.07
    gings
    0.07
    벱
    0.07
    Studio
    0.07
    standen
    0.07
     buyers
    0.07
    月中旬
    0.06
    iev
    0.06
    Act Density 0.005%

    No Known Activations