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

    Neuronpedia

    INDEX
    Explanations

    obstruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서를
    0.71
    antz
    0.70
    acular
    0.67
    циях
    0.67
     seaw
    0.66
     corta
    0.66
    errick
    0.65
    ↔
    0.64
     comparatively
    0.64
    IFF
    0.64
    POSITIVE LOGITS
     dukungan
    0.82
     pendidikan
    0.79
    vý
    0.79
     gagn
    0.77
     lý
    0.75
    ný
    0.75
     mengembangkan
    0.75
    يين
    0.74
     uygulan
    0.74
     logique
    0.73
    Act Density 0.003%

    No Known Activations