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

    Neuronpedia

    INDEX
    Explanations

    common actions and beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.50
     genres
    0.45
    izei
    0.43
    ünd
    0.41
     conductors
    0.41
     screenplay
    0.41
    uvos
    0.40
     comedies
    0.39
     spectacle
    0.39
     hugged
    0.39
    POSITIVE LOGITS
     rychle
    0.49
    ೭
    0.45
    葚
    0.45
     místo
    0.45
     często
    0.44
     spesso
    0.44
    人も
    0.44
    ৮
    0.43
    なんと
    0.43
    重视
    0.42
    Act Density 0.003%

    No Known Activations