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

    Neuronpedia

    INDEX
    Explanations

    roux blocks or PPO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JSX
    0.54
     gota
    0.52
     JWT
    0.47
     tvr
    0.45
    ↵↵
    0.44
     proiect
    0.44
    L
    0.44
    뵈
    0.43
     Mart
    0.43
     récip
    0.42
    POSITIVE LOGITS
     epidemiological
    0.52
    संख्यक
    0.50
    വര്‍
    0.48
     സര്‍
    0.48
     സര്‍ക്കാര്‍
    0.48
     policymakers
    0.47
     empat
    0.47
     uncorrelated
    0.47
    ุ
    0.47
    的应用
    0.47
    Act Density 0.000%

    No Known Activations