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

    Neuronpedia

    INDEX
    Explanations

    taxi or ride-sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дравствуйте
    1.09
    もら
    1.07
    requis
    1.06
    de
    1.00
    ity
    0.97
    terer
    0.95
     fronte
    0.94
    на
    0.93
    словия
    0.93
    वट
    0.93
    POSITIVE LOGITS
     syringe
    1.02
    ح
    0.91
    、、、
    0.90
     cabs
    0.88
     kereta
    0.88
    მართ
    0.88
    ยนต์
    0.87
    즘
    0.87
    utm
    0.85
    こそ
    0.85
    Act Density 0.009%

    No Known Activations