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

    Neuronpedia

    INDEX
    Explanations

    often contribute to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     était
    0.46
     präsent
    0.46
     gleiche
    0.46
    வ்வாறு
    0.45
     була
    0.45
    枃
    0.43
     entwickeln
    0.43
     із
    0.42
     ഗെയി
    0.42
     зі
    0.41
    POSITIVE LOGITS
     one
    0.42
     client
    0.40
     capital
    0.40
     vegetarian
    0.38
     Tid
    0.38
     Lament
    0.38
     C
    0.37
     tomorrow
    0.37
     pounds
    0.37
     dumplings
    0.37
    Act Density 0.000%

    No Known Activations