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

    Neuronpedia

    INDEX
    Explanations

    critiques, arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مین
    -0.07
     residence
    -0.07
     Junior
    -0.06
     relocated
    -0.06
    ipline
    -0.06
     정책
    -0.06
    ゃ
    -0.06
     Guidelines
    -0.06
    -led
    -0.06
     автомати
    -0.06
    POSITIVE LOGITS
    				
↵
    0.07
     uphe
    0.06
    styleType
    0.06
    contact
    0.06
     wieder
    0.06
    owing
    0.06
    alance
    0.06
     BigInt
    0.06
    uly
    0.06
     св
    0.06
    Act Density 0.036%

    No Known Activations