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

    Neuronpedia

    INDEX
    Explanations

    numbers and non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Baillargeon
    0.40
    wyczaj
    0.40
     علامه
    0.37
    Ca
    0.37
    幸福
    0.35
    標
    0.35
    ితి
    0.35
     ém
    0.35
    jours
    0.35
    igenschaft
    0.35
    POSITIVE LOGITS
    ាញ់
    0.52
    ฎ
    0.46
     பராம
    0.41
    ตน
    0.40
    stationary
    0.38
     Great
    0.38
     neigh
    0.38
     ("/
    0.37
     Mahoney
    0.37
     ড্র
    0.36
    Act Density 0.000%

    No Known Activations