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

    Neuronpedia

    INDEX
    Explanations

    placeholders and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஒரு
    0.69
    Major
    0.68
    Hash
    0.66
    অন্য
    0.66
    Ле
    0.66
    От
    0.65
    ੋਂ
    0.63
    Лю
    0.63
    У
    0.63
    Я
    0.62
    POSITIVE LOGITS
    となる
    0.68
    ary
    0.67
    적인
    0.66
     version
    0.64
     plantings
    0.64
     feelings
    0.63
    ingly
    0.62
     mentality
    0.61
     scenario
    0.60
     phrasing
    0.60
    Act Density 0.440%

    No Known Activations