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

    Neuronpedia

    INDEX
    Explanations

    friendships and interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ์
    2.58
    ه
    2.33
    이
    2.16
    ம்
    2.05
    শ
    2.01
    nae
    2.00
    й
    1.96
    ள்ள
    1.95
    к
    1.94
     impulse
    1.93
    POSITIVE LOGITS
    ส์
    2.26
    𝑅
    2.25
    it
    2.21
     відбувається
    2.15
    ()=>{
    2.15
    piperidin
    2.14
    ۰
    2.11
    ように
    2.09
    𝐷
    2.06
    ان
    2.05
    Act Density 0.074%

    No Known Activations