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

    Neuronpedia

    INDEX
    Explanations

    academic paper citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     similarity
    0.33
    ುತ್ತೇವೆ
    0.32
     Similarity
    0.31
     Astrophysical
    0.30
     EEC
    0.30
     Thousand
    0.29
    ುತ್ತಾರೆ
    0.29
    ម្បី
    0.29
    न्होंने
    0.29
    ುತ್ತವೆ
    0.29
    POSITIVE LOGITS
     १५
    0.50
     १६
    0.46
     १०
    0.42
     ८
    0.41
     २५
    0.40
     ૨
    0.40
     २००
    0.40
     ७
    0.38
    १९
    0.38
    0.38
    Act Density 0.002%

    No Known Activations