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

    Neuronpedia

    INDEX
    Explanations

    crucial that, needing transport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.52
     thereof
    0.49
     approximate
    0.46
    International
    0.46
     announced
    0.44
    ILL
    0.44
     দীপ
    0.44
    ____
    0.44
    '
    0.44
    ß
    0.44
    POSITIVE LOGITS
     Xem
    0.51
     عش
    0.46
    족
    0.46
    tileSize
    0.45
     computerChoice
    0.43
    溪
    0.42
    男生
    0.42
     közé
    0.42
    chés
    0.42
    labeled
    0.40
    Act Density 0.001%

    No Known Activations