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

    Neuronpedia

    INDEX
    Explanations

    design collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scary
    -0.07
     SCR
    -0.07
    铠
    -0.07
     Murphy
    -0.07
    总队
    -0.07
     crippled
    -0.07
    灭火
    -0.06
    planes
    -0.06
     zes
    -0.06
    )})↵
    -0.06
    POSITIVE LOGITS
    同情
    0.08
    огда
    0.08
    Plant
    0.08
    的方式来
    0.07
    typeparam
    0.07
    .family
    0.07
    ồn
    0.07
     uży
    0.07
    股价
    0.07
    _yield
    0.07
    Act Density 0.042%

    No Known Activations