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

    Neuronpedia

    INDEX
    Explanations

    causes and influences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alarını
    0.37
     आर्मी
    0.36
    ئو
    0.36
    ෙක්
    0.36
    қта
    0.36
    政府采购
    0.35
     pärast
    0.35
    适用于
    0.35
    گان
    0.34
    Panning
    0.34
    POSITIVE LOGITS
     influences
    0.89
     влияет
    0.88
     factors
    0.77
     affects
    0.76
     influence
    0.73
     beeinfl
    0.73
     affect
    0.72
    因素
    0.71
    影響
    0.70
     influencing
    0.70
    Act Density 0.303%

    No Known Activations