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

    Neuronpedia

    INDEX
    Explanations

    seems to be about order and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distill
    0.88
    Alcohol
    0.77
    Sector
    0.74
     ход
    0.72
    Anthrop
    0.72
    льності
    0.72
    世界
    0.71
    ደጋ
    0.70
    помним
    0.70
     smooth
    0.70
    POSITIVE LOGITS
     erhielt
    0.96
     erhält
    0.82
     gezeigt
    0.81
     angesehen
    0.81
     vaikka
    0.80
    ner
    0.78
    𝖾
    0.77
     obtuvo
    0.76
     erricht
    0.75
     möchten
    0.75
    Act Density 0.000%

    No Known Activations