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

    Neuronpedia

    INDEX
    Explanations

    continue explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ചില
    0.45
     subfamily
    0.43
    ᐢ
    0.43
    Stor
    0.43
    └──
    0.43
    Roger
    0.42
    ≧
    0.42
     দিয়
    0.41
    োয়া
    0.40
    िखित
    0.40
    POSITIVE LOGITS
     continue
    0.51
     Continue
    0.48
     Mostrar
    0.47
    continue
    0.47
     continúa
    0.46
     continues
    0.46
     Дет
    0.45
     Take
    0.45
    त्रा
    0.45
     One
    0.44
    Act Density 0.156%

    No Known Activations