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

    Neuronpedia

    INDEX
    Explanations

    huggingface or helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </b>
    0.71
     view
    0.70
     अब
    0.67
     (
    0.66
     swipe
    0.66
     وی
    0.65
     eventually
    0.64
     की
    0.63
     averaging
    0.62
     which
    0.60
    POSITIVE LOGITS
     gyven
    0.92
     hablan
    0.91
     kompet
    0.90
    amiseks
    0.89
     spolupr
    0.88
    <unused60>
    0.88
    ClFN
    0.87
    βέρ
    0.85
     reikia
    0.84
    Thông
    0.84
    Act Density 0.038%

    No Known Activations