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

    Neuronpedia

    INDEX
    Explanations

    unstructured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڨ
    0.50
     niña
    0.49
     avantages
    0.48
     exclusiva
    0.47
     parceria
    0.46
    ઠળ
    0.46
     octubre
    0.46
     oublier
    0.46
     условиях
    0.46
    ه‌ی
    0.46
    POSITIVE LOGITS
    anes
    0.43
     کررہ
    0.41
     계속
    0.40
     BIOS
    0.38
    cheduling
    0.38
     움직
    0.37
     (
    0.36
     nears
    0.36
     seems
    0.35
     scanned
    0.35
    Act Density 0.006%

    No Known Activations