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

    Neuronpedia

    INDEX
    Explanations

    nodes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ',

↵
    -0.07
    电信
    -0.07
    terminate
    -0.07
    ipation
    -0.07
    财运
    -0.07
    씀
    -0.07
    .shopping
    -0.07
    	load
    -0.07
    涔
    -0.07
     likelihood
    -0.06
    POSITIVE LOGITS
     Subscription
    0.08
    ="""
    0.07
    -results
    0.07
     оборудования
    0.07
    览
    0.06
    pure
    0.06
    全是
    0.06
    argin
    0.06
    .’”↵↵
    0.06
     EXISTS
    0.06
    Act Density 0.025%

    No Known Activations