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

    Neuronpedia

    INDEX
    Explanations

    whether

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resolves
    -0.08
    ác
    -0.07
    leground
    -0.07
     А
    -0.07
    �
    -0.07
     Bread
    -0.06
    енсив
    -0.06
    into
    -0.06
     )↵↵↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    创新
    0.07
    array
    0.06
    调整
    0.06
    Search
    0.06
     Pv
    0.06
     입력
    0.06
    SEARCH
    0.06
    _taxonomy
    0.06
    ensemble
    0.06
    .parsers
    0.06
    Act Density 0.008%

    No Known Activations