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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric hashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     navy
    0.28
     take
    0.26
     splic
    0.26
     abnorm
    0.26
     primit
    0.25
     outfit
    0.25
     hous
    0.25
     Outfit
    0.25
     pixel
    0.25
     vuttam
    0.25
    POSITIVE LOGITS
    до
    0.32
    possibly
    0.31
    ர்க
    0.30
    ся
    0.30
    rest
    0.30
    potentially
    0.30
    і
    0.30
    дель
    0.29
    с
    0.29
    да
    0.29
    Act Density 0.019%

    No Known Activations