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

    Neuronpedia

    INDEX
    Explanations

    comprehensive, established, implementing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ภัย
    0.35
    geon
    0.34
    Dean
    0.34
    '$.
    0.32
     γεγον
    0.31
    deployed
    0.31
    }}{(
    0.31
     nut
    0.31
    কাম
    0.31
    \(
    0.30
    POSITIVE LOGITS
     budú
    0.40
     sitios
    0.39
    াহিয়া
    0.39
     વિવિધ
    0.39
    琇
    0.39
     রোগী
    0.38
     nieder
    0.38
     intérieur
    0.37
     আসল
    0.37
    צוני
    0.37
    Act Density 0.000%

    No Known Activations