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

    Neuronpedia

    INDEX
    Explanations

    know what, know more, know everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াদ
    0.32
    adip
    0.31
     لاحظ
    0.30
    говой
    0.30
    slideDuplicate
    0.30
    បំ
    0.30
    ueel
    0.30
    াল
    0.29
    මට
    0.29
     معك
    0.29
    POSITIVE LOGITS
     about
    0.59
     firsthand
    0.54
    lege
    0.52
     intimately
    0.51
     instinctively
    0.50
    ledged
    0.48
    ledge
    0.48
    ingly
    0.48
     whereof
    0.47
     better
    0.45
    Act Density 0.019%

    No Known Activations