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

    Neuronpedia

    INDEX
    Explanations

    positive feedback and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wanted
    0.45
    鋰
    0.44
     weder
    0.44
     합동
    0.43
     wollte
    0.43
     diversos
    0.43
    various
    0.43
    vers
    0.42
    eric
    0.41
    ೮
    0.41
    POSITIVE LOGITS
    Gig
    0.45
    Parsed
    0.45
     shortlist
    0.43
    Recent
    0.43
    Runner
    0.41
    Fixture
    0.41
    Preview
    0.41
    Rendering
    0.40
    ником
    0.40
     بالإضافة
    0.40
    Act Density 0.014%

    No Known Activations