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

    Neuronpedia

    INDEX
    Explanations

    every step of the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synthes
    0.53
    \
    0.53
    ların
    0.52
    <0xAF>
    0.50
    在其
    0.50
     phospholipid
    0.49
    с
    0.49
    MAN
    0.48
     Judgment
    0.48
     tử
    0.47
    POSITIVE LOGITS
    t
    0.93
    tive
    0.60
    tiger
    0.60
    tif
    0.56
    college
    0.55
    ারা
    0.55
     evoke
    0.54
     ovviamente
    0.54
    Riv
    0.54
    l
    0.54
    Act Density 0.002%

    No Known Activations