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

    Neuronpedia

    INDEX
    Explanations

    explaining ease and meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :")
    0.47
     거리
    0.47
     போலவே
    0.46
     vrijeme
    0.44
     نہيں
    0.44
     близо
    0.42
    の一部
    0.42
     bebidas
    0.41
     imbued
    0.41
     домаш
    0.41
    POSITIVE LOGITS
    褰
    0.49
    <0xAF>
    0.49
    t
    0.47
     Vi
    0.44
    Vi
    0.43
     viktigt
    0.43
    先進
    0.43
    utions
    0.43
    νον
    0.42
    先进
    0.42
    Act Density 0.002%

    No Known Activations