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

    Neuronpedia

    INDEX
    Explanations

    skill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amba
    -0.08
    📖
    -0.08
    难度
    -0.07
    肚子
    -0.07
    咏
    -0.07
    处处
    -0.07
    _DOCUMENT
    -0.07
    _lambda
    -0.07
    跟不上
    -0.07
    🚗
    -0.07
    POSITIVE LOGITS
     stored
    0.08
    		  ↵
    0.08
     celui
    0.07
     aired
    0.07
     coil
    0.07
    	l
    0.07
     registrado
    0.07
     Gate
    0.07
    Credit
    0.07
    软
    0.07
    Act Density 0.008%

    No Known Activations