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

    Neuronpedia

    INDEX
    Explanations

    frogs, wolves, cows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Народ
    0.52
     முற
    0.50
     ద్వారా
    0.50
     доб
    0.50
     இந்நிலையில்
    0.50
     Мен
    0.49
     जिज्ञासा
    0.49
    Benzoimidazol
    0.47
     प्रदर्शन
    0.47
     குறைவாக
    0.47
    POSITIVE LOGITS
    a
    0.46
    ܦ
    0.46
    and
    0.43
    til
    0.41
    eight
    0.41
    austral
    0.41
    Flair
    0.41
    8
    0.40
    ه
    0.40
    ８
    0.40
    Act Density 0.001%

    No Known Activations