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

    Neuronpedia

    INDEX
    Explanations

    cryptographer, Autopilot, nanotubes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GDPR
    0.73
     Fabric
    0.70
     bingo
    0.69
     Unix
    0.68
     UFC
    0.67
     Ruby
    0.66
     Dik
    0.65
     Pie
    0.65
     WWE
    0.65
     Ring
    0.65
    POSITIVE LOGITS
    ological
    1.70
    ocom
    1.62
    opro
    1.59
    ogenic
    1.55
    olog
    1.54
    opol
    1.54
    ographic
    1.50
    oph
    1.49
    op
    1.46
    ologic
    1.46
    Act Density 0.409%

    No Known Activations