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

    Neuronpedia

    INDEX
    Explanations

    significantly larger, actively engaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    0.90
    ры
    0.86
    ం
    0.82
     Некоторые
    0.77
    ,\,\,\,\
    0.75
    Qaeda
    0.74
     неболь
    0.72
     منها
    0.71
     треуго
    0.71
     उपचुनाव
    0.71
    POSITIVE LOGITS
    🥩
    0.79
    🥅
    0.72
    glightbox
    0.71
     Subjects
    0.70
    #
    0.70
    𝑻
    0.69
     Arthritis
    0.68
    essing
    0.67
    situ
    0.66
    🛋
    0.66
    Act Density 0.001%

    No Known Activations