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

    Neuronpedia

    INDEX
    Explanations

    punctuation and list structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.61
    It
    0.55
     It
    0.54
    <unused335>
    0.49
    They
    0.48
    simply
    0.47
    s
    0.45
    ों
    0.44
    <unused284>
    0.44
     который
    0.44
    POSITIVE LOGITS
    ，
    0.70
    ،
    0.69
    (),
    0.56
    。
    0.50
     (
    0.49
    $,
    0.49
    0.48
    》，
    0.46
    ))
    0.46
    ,
    0.46
    Act Density 0.075%

    No Known Activations