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

    Neuronpedia

    INDEX
    Explanations

    multilingual verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.65
    er
    0.64
    and
    0.63
    it
    0.61
    od
    0.56
    ai
    0.56
    ag
    0.54
    ER
    0.54
    aiya
    0.54
    dür
    0.53
    POSITIVE LOGITS
     in
    0.77
    ى
    0.71
    м
    0.66
    ts
    0.64
    с
    0.63
    س
    0.63
     في
    0.60
     volna
    0.59
    מ
    0.57
    ，
    0.55
    Act Density 0.004%

    No Known Activations