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

    Neuronpedia

    INDEX
    Explanations

    addressing airway-centered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.34
     сове
    0.31
     COR
    0.30
     앞
    0.30
    ра
    0.30
     DISC
    0.29
     갑
    0.29
     Forge
    0.28
     anak
    0.28
     Una
    0.28
    POSITIVE LOGITS
    咱们
    0.42
    Hence
    0.42
    Their
    0.40
    Addressing
    0.39
     انہیں
    0.38
    他们
    0.38
    इसका
    0.38
    Seems
    0.37
    他們
    0.37
     उनको
    0.36
    Act Density 5.901%

    No Known Activations