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

    Neuronpedia

    INDEX
    Explanations

    to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.64
    .
    0.63
    s
    0.54
    k
    0.54
    র
    0.50
    с
    0.50
    ."
    0.48
    p
    0.48
    m
    0.48
    ー
    0.48
    POSITIVE LOGITS
     fruition
    0.63
    极致
    0.54
    ppled
    0.53
     stardom
    0.53
    userDetail
    0.53
     electrification
    0.52
    pless
    0.51
     standstill
    0.51
    搛
    0.48
     shreds
    0.48
    Act Density 0.058%

    No Known Activations