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

    Neuronpedia

    INDEX
    Explanations

    list item formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mathbf
    0.89
    '>");
    0.70
     hinn
    0.63
    io
    0.61
    ";//
    0.61
    umber
    0.60
     $\%$
    0.59
    uern
    0.59
    .%
    0.59
    :%
    0.58
    POSITIVE LOGITS
    <i>
    2.17
    <em>
    2.17
    《
    2.12
     《
    2.05
     /*
    1.95
    /*
    1.92
     『
    1.86
    ，《
    1.75
    『
    1.73
     _
    1.58
    Act Density 0.145%

    No Known Activations