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

    Neuronpedia

    INDEX
    Explanations

    lobbying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    儿
    -0.07
    _ori
    -0.07
     Assange
    -0.06
    Categories
    -0.06
     bir
    -0.06
     Voyager
    -0.06
    leo
    -0.06
    兒
    -0.06
    aha
    -0.06
    AEA
    -0.06
    POSITIVE LOGITS
     виход
    0.08
    .listBox
    0.07
    ulnerable
    0.07
    .toBe
    0.06
    	Resource
    0.06
     dla
    0.06
    ]");↵
    0.06
    ATORY
    0.06
     клет
    0.06
     ></
    0.06
    Act Density 0.024%

    No Known Activations