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

    Neuronpedia

    INDEX
    Explanations

    & followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اب
    1.23
    ח
    1.23
    なかなか
    1.21
    ر
    1.10
    も
    1.10
    しかし
    1.09
    أن
    1.06
    した
    1.02
    й
    1.02
    ă
    1.02
    POSITIVE LOGITS
     whatnot
    1.23
    ndash
    1.20
    mdash
    1.07
    ne
    1.05
    ায়
    1.02
    romeda
    1.02
    rogens
    0.98
    amp
    0.92
     firef
    0.89
     Subsidi
    0.89
    Act Density 0.910%

    No Known Activations