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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     금
    -0.07
     _______,
    -0.06
    afb
    -0.06
    泡
    -0.06
    adalafil
    -0.06
     hvad
    -0.06
     �
    -0.06
    湿
    -0.06
     pem
    -0.06
    rana
    -0.05
    POSITIVE LOGITS
    ())){↵
    0.07
     ]
↵
    0.07
    	console
    0.07
    -court
    0.06
    ])){↵
    0.06
    ヤ
    0.06
    ATURE
    0.06
    '});↵
    0.06
     Doctors
    0.06
    astic
    0.06
    Act Density 0.001%

    No Known Activations