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

    Neuronpedia

    INDEX
    Explanations

    the **i** suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overload
    0.40
    गंज
    0.40
    िटेशन
    0.39
    νό
    0.38
     Quay
    0.38
     ट्रोल
    0.38
    <>());
    0.37
    फिक
    0.37
     bath
    0.37
    Attractive
    0.37
    POSITIVE LOGITS
    ilea
    0.63
    lea
    0.53
    cea
    0.52
    zea
    0.50
     lea
    0.48
    dea
    0.44
    alea
    0.43
    sea
    0.43
    fea
    0.43
    ̉a
    0.42
    Act Density 0.000%

    No Known Activations