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

    Neuronpedia

    INDEX
    Explanations

    busbuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asic
    0.63
     peta
    0.60
     terhadap
    0.56
    ลักษณ์
    0.54
     matchup
    0.53
     Independent
    0.52
    esque
    0.52
    t
    0.52
     Underwater
    0.51
    g
    0.51
    POSITIVE LOGITS
     buses
    1.34
     автобу
    1.22
     bus
    1.16
     busses
    1.11
     Buses
    1.10
     बसों
    1.06
    Bus
    1.01
    🚌
    0.99
    バス
    0.95
     ônibus
    0.95
    Act Density 0.013%

    No Known Activations