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

    Neuronpedia

    INDEX
    Explanations

    writing word count specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ध
    0.32
     sagging
    0.29
     sagen
    0.27
     sc
    0.27
     ناقص
    0.26
     sow
    0.26
     partículas
    0.26
     رغم
    0.26
     contractions
    0.26
     apes
    0.26
    POSITIVE LOGITS
    akan
    0.31
    University
    0.30
    inis
    0.29
    astudio
    0.29
    ชัย
    0.29
    Само
    0.29
     Университе
    0.29
    Director
    0.28
    Detailed
    0.28
    Executive
    0.28
    Act Density 0.020%

    No Known Activations