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

    Neuronpedia

    INDEX
    Explanations

    simplifies calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theme
    0.66
     themed
    0.66
    themed
    0.64
     themes
    0.63
    主题
    0.63
    Themes
    0.62
    テーマ
    0.61
     thème
    0.59
     thematic
    0.58
     थीम
    0.58
    POSITIVE LOGITS
    ARIES
    0.38
    Nov
    0.37
     CIN
    0.37
    CIN
    0.37
     covari
    0.36
    ਕਾਰ
    0.36
    Rebecca
    0.36
     décrire
    0.36
     senescence
    0.36
    rifice
    0.36
    Act Density 0.000%

    No Known Activations