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

    Neuronpedia

    INDEX
    Explanations

    Spanish autonomous communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usuario
    0.50
    ўся
    0.49
     शहरा
    0.49
    vill
    0.48
    라인
    0.48
    շ
    0.48
    쉘
    0.48
    vykor
    0.47
    ciudad
    0.47
    ę
    0.47
    POSITIVE LOGITS
    :
    0.71
     (
    0.55
    Leftrightarrow
    0.53
     Lage
    0.52
     -
    0.52
     and
    0.51
     Sagan
    0.50
    0.50
     Solubility
    0.50
     L
    0.49
    Act Density 0.001%

    No Known Activations