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

    Neuronpedia

    INDEX
    Explanations

    a lightly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.71
    ان
    0.63
    c
    0.62
     as
    0.59
     adverts
    0.59
    הר
    0.58
    לה
    0.55
    a
    0.54
    r
    0.53
     اعلان
    0.52
    POSITIVE LOGITS
     सब्जियों
    0.63
    abilă
    0.61
     сельского
    0.61
     मार्क्स
    0.59
     एग्रीकल्चर
    0.59
    rizes
    0.58
     समस्या
    0.58
     टिश्यू
    0.58
    royal
    0.57
     Tetrahedron
    0.55
    Act Density 0.000%

    No Known Activations