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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    norm
    -0.07
     McKay
    -0.06
    ४
    -0.06
     puzz
    -0.06
    █
    -0.06
    ३
    -0.06
    Teen
    -0.06
    Nu
    -0.06
    eat
    -0.06
     Weeks
    -0.06
    POSITIVE LOGITS
    硬
    0.07
     stiffness
    0.07
    _TOPIC
    0.06
     мере
    0.06
    ταση
    0.06
    '}↵
    0.06
     rarely
    0.06
     кожи
    0.06
     üret
    0.06
     دیگر
    0.06
    Act Density 0.009%

    No Known Activations