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

    Neuronpedia

    INDEX
    Explanations

    geographical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     گزشتہ
    0.48
     தெரிவித்த
    0.44
     СССР
    0.43
     Drops
    0.42
    付出
    0.42
     setia
    0.42
    霾
    0.42
     Roskov
    0.41
     ماس
    0.41
     Estados
    0.41
    POSITIVE LOGITS
    <0x89>
    0.61
    are
    0.58
    ich
    0.55
    ید
    0.55
    ân
    0.54
    the
    0.53
    city
    0.53
     miasta
    0.52
    divided
    0.50
    and
    0.49
    Act Density 0.038%

    No Known Activations