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

    Neuronpedia

    INDEX
    Explanations

    Numbers/Measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.61
    0
    -0.60
    don
    -0.51
    ,
    -0.50
    ↵↵
    -0.50
    k
    -0.50
    <eos>
    -0.50
    m
    -0.49
    ila
    -0.49
    +
    -0.48
    POSITIVE LOGITS
    "])
    0.79
    AnchorStyles
    0.78
    "]
    0.71
     endfor
    0.69
    ']]
    0.68
    ']))
    0.68
    '])){
    0.68
    ']);
    0.67
    "];
    0.66
    '])
    0.66
    Act Density 0.004%

    No Known Activations