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

    Neuronpedia

    INDEX
    Explanations

    unconventional alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бү
    0.35
     obtuvo
    0.34
    খন
    0.31
     التعليم
    0.30
    迄
    0.30
     hören
    0.29
     সম্মানিত
    0.29
    ভূ
    0.29
    Cafe
    0.29
     perfetto
    0.29
    POSITIVE LOGITS
     unconventional
    0.34
     invece
    0.33
     بجائے
    0.33
     instead
    0.32
    じゃない
    0.32
     unlike
    0.32
     zami
    0.32
     paucity
    0.32
     Instead
    0.31
     대신
    0.31
    Act Density 0.041%

    No Known Activations