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

    Neuronpedia

    INDEX
    Explanations

    stop at red lights or signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     откри
    0.42
     apuesta
    0.40
     rápido
    0.39
     rých
    0.35
     descoberta
    0.35
    qb
    0.35
     chinos
    0.34
     قيم
    0.34
     softmax
    0.34
     zlep
    0.34
    POSITIVE LOGITS
     কণ্
    0.44
     North
    0.42
    cester
    0.42
     conç
    0.41
     diatom
    0.40
     unnamed
    0.39
    North
    0.39
    τεί
    0.39
    叁
    0.38
    kamer
    0.38
    Act Density 0.000%

    No Known Activations