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

    Neuronpedia

    INDEX
    Explanations

    traffic control and accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    டன்
    0.99
    kę
    0.96
    ként
    0.96
     for
    0.91
     electrón
    0.84
    kc
    0.84
    ك
    0.84
     in
    0.83
     afectar
    0.82
     impulsar
    0.82
    POSITIVE LOGITS
    is
    1.46
    ad
    1.28
    ik
    1.13
    ли
    1.10
    q
    1.09
    И
    1.06
    ak
    1.04
    Traffic
    1.02
    ing
    0.99
    не
    0.96
    Act Density 0.006%

    No Known Activations