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

    Neuronpedia

    INDEX
    Explanations

    works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    对她
    -0.08
     subprocess
    -0.07
     уч
    -0.07
    =path
    -0.07
    -Nov
    -0.06
    �
    -0.06
    稽
    -0.06
    @test
    -0.06
     adress
    -0.06
    	search
    -0.06
    POSITIVE LOGITS
    这样一
    0.07
     iconic
    0.07
     innovative
    0.07
    安徽
    0.07
    ernational
    0.06
    书记
    0.06
     enumeration
    0.06
    饧
    0.06
    粉碎
    0.06
    ysi
    0.06
    Act Density 0.291%

    No Known Activations