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

    Neuronpedia

    INDEX
    Explanations

    understand transmissions and identities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moyen
    0.54
    a
    0.51
     Sushi
    0.50
     Textiles
    0.49
    Sushi
    0.48
    Wenn
    0.46
    zieht
    0.46
    urte
    0.45
    atoires
    0.44
    A
    0.44
    POSITIVE LOGITS
    🔹
    0.47
    📒
    0.47
    迅
    0.46
    人口
    0.44
     sow
    0.42
     disturbance
    0.42
    なく
    0.42
    細胞
    0.42
    可能
    0.41
     sentimento
    0.41
    Act Density 0.000%

    No Known Activations