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

    Neuronpedia

    INDEX
    Explanations

    natural stresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᒐ
    0.41
    0.39
    bigskip
    0.39
    0.38
    
    0.38
    0.37
     परस्पर
    0.36
    $_{
    0.36
    とする
    0.35
    0.35
    POSITIVE LOGITS
     Eagles
    0.42
     Football
    0.41
     Wildlife
    0.40
     خیلی
    0.40
     Rangers
    0.39
    ون
    0.38
     Adidas
    0.37
     حتى
    0.36
     Logistics
    0.36
     Derby
    0.36
    Act Density 0.002%

    No Known Activations