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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleanliness
    -0.07
     mux
    -0.07
    测试
    -0.07
    _uploaded
    -0.07
    .runner
    -0.07
    _FLOAT
    -0.07
    ponent
    -0.07
     factorial
    -0.07
    cem
    -0.07
    roring
    -0.07
    POSITIVE LOGITS
     Bakanlığı
    0.06
     Interfaces
    0.06
     bombing
    0.06
    Eth
    0.06
    generate
    0.06
    ぶ
    0.06
    _evt
    0.06
    ़ें
    0.06
     moci
    0.06
     Churches
    0.06
    Act Density 0.003%

    No Known Activations