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

    Neuronpedia

    INDEX
    Explanations

    Social media captions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    柈
    -0.08
     Coil
    -0.07
     lia
    -0.07
     divided
    -0.07
     масло
    -0.07
     Speakers
    -0.07
     Devils
    -0.06
    硫酸
    -0.06
    Rotor
    -0.06
    Ꮎ
    -0.06
    POSITIVE LOGITS
     eyebrow
    0.07
    特别
    0.07
     Iterate
    0.07
     Authorization
    0.07
    参考
    0.07
    )".
    0.07
    🏓
    0.06
    被称为
    0.06
    -index
    0.06
    .decor
    0.06
    Act Density 0.074%

    No Known Activations