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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vogue
    0.47
     Gifts
    0.43
     Ausstattung
    0.43
     unisex
    0.43
     Unisex
    0.43
     বৃহৎ
    0.42
    thrust
    0.42
    null
    0.42
     ক্লিক
    0.42
     Jo
    0.41
    POSITIVE LOGITS
     criminals
    0.53
     murderers
    0.51
     theories
    0.47
     cotidiana
    0.47
     policemen
    0.46
     policías
    0.46
     cartoons
    0.45
     ourselves
    0.44
     cotidian
    0.43
     scares
    0.42
    Act Density 0.005%

    No Known Activations