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

    Neuronpedia

    INDEX
    Explanations

    brake lines, 988

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gospod
    0.60
    inete
    0.59
    琶
    0.59
    omega
    0.56
     मांगने
    0.55
     Room
    0.53
    fetchAll
    0.53
     Sen
    0.53
    вет
    0.53
    ogl
    0.52
    POSITIVE LOGITS
     अधिव
    0.63
     trustee
    0.62
     dosis
    0.62
     nobles
    0.61
     tribal
    0.61
     newspaper
    0.60
    arrêter
    0.58
     ಕಾನೂ
    0.58
     सिंधु
    0.58
     temporary
    0.58
    Act Density 0.211%

    No Known Activations