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

    Neuronpedia

    INDEX
    Explanations

    inary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obot
    -0.07
     berk
    -0.07
     bourgeois
    -0.07
    $k
    -0.07
     ck
    -0.07
     côté
    -0.07
    战斗
    -0.07
    ück
    -0.07
     zaměstnan
    -0.06
    _action
    -0.06
    POSITIVE LOGITS
     urinary
    0.09
     urine
    0.08
     urgent
    0.08
     uncomment
    0.07
    /al
    0.06
     Serbia
    0.06
    าเล
    0.06
     stderr
    0.06
    .prev
    0.06
    /mp
    0.06
    Act Density 0.011%

    No Known Activations