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

    Neuronpedia

    INDEX
    Explanations

    structural headings and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cdZ
    0.42
    нон
    0.39
     pilot
    0.37
    ەد
    0.37
     subset
    0.37
     coars
    0.35
     codimension
    0.34
     sott
    0.33
     ισ
    0.33
    یدہ
    0.32
    POSITIVE LOGITS
    <h3>
    0.47
    Note
    0.46
    हम
    0.44
    Each
    0.43
    <h2>
    0.42
    There
    0.40
    These
    0.40
     Note
    0.39
    <h4>
    0.39
    For
    0.38
    Act Density 0.000%

    No Known Activations