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

    Neuronpedia

    INDEX
    Explanations

    HTML heading and bold tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diesem
    0.55
    ْن
    0.55
     данном
    0.55
    лі
    0.54
     }}=
    0.51
     przypadku
    0.50
    /*',
    0.49
    лися
    0.49
    țele
    0.49
    があり
    0.48
    POSITIVE LOGITS
    <h2>
    1.03
    ↵↵↵
    0.93
    <h1>
    0.84
    <h3>
    0.83
    ##
    0.73
    ↵↵↵↵↵
    0.73
    ↵↵↵↵
    0.72
    <b>
    0.72
    <h4>
    0.70
    <strong>
    0.65
    Act Density 0.382%

    No Known Activations