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

    Neuronpedia

    INDEX
    Explanations

    things you can taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bytes
    0.39
    omponent
    0.38
    pupp
    0.38
     terrorism
    0.36
    adins
    0.36
     chuột
    0.36
     ASA
    0.35
    ans
    0.35
    aps
    0.35
     ballots
    0.35
    POSITIVE LOGITS
     taste
    0.66
     вкус
    0.64
     tastes
    0.62
    味わ
    0.60
    Taste
    0.59
     tasting
    0.59
     स्वाद
    0.59
     goût
    0.58
    taste
    0.57
     Taste
    0.57
    Act Density 0.012%

    No Known Activations