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

    Neuronpedia

    INDEX
    Explanations

    Cre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feels
    -0.07
    自然是
    -0.07
     remake
    -0.07
     ETH
    -0.07
    “That
    -0.07
    棕色
    -0.07
    (owner
    -0.06
     Fill
    -0.06
    	info
    -0.06
    	selected
    -0.06
    POSITIVE LOGITS
    entityManager
    0.07
     dbl
    0.07
    _refer
    0.06
    hausen
    0.06
    �
    0.06
    贽
    0.06
    ქ
    0.06
    迟
    0.06
     regul
    0.06
    康
    0.06
    Act Density 0.002%

    No Known Activations