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

    Neuronpedia

    INDEX
    Explanations

    synchronous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	label
    -0.07
     vectors
    -0.07
     vector
    -0.07
    (ele
    -0.07
    	Integer
    -0.06
    人口
    -0.06
    culated
    -0.06
    em
    -0.06
    .validators
    -0.06
     elite
    -0.06
    POSITIVE LOGITS
    .async
    0.08
     Andy
    0.08
    Andy
    0.08
    ASY
    0.07
    까
    0.07
     asynchronous
    0.07
    います
    0.07
    спіль
    0.07
     utc
    0.07
    προ
    0.07
    Act Density 0.007%

    No Known Activations