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

    Neuronpedia

    INDEX
    Explanations

    numbers, symbols, and specific dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barang
    0.42
     zowel
    0.40
     kund
    0.39
     instill
    0.39
     süreç
    0.39
     pohon
    0.38
     ambil
    0.38
     infrast
    0.37
     ۴
    0.37
     yattha
    0.37
    POSITIVE LOGITS
    one
    0.43
    os
    0.41
     This
    0.40
    this
    0.40
    <0xB8>
    0.39
    This
    0.39
    3
    0.37
    R
    0.37
    ed
    0.36
    ви
    0.36
    Act Density 0.011%

    No Known Activations