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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ughty
    -0.07
    ㌧
    -0.07
    缫
    -0.07
    حب
    -0.07
    unque
    -0.06
    都需要
    -0.06
    .capture
    -0.06
     как
    -0.06
    adiens
    -0.06
    ском
    -0.06
    POSITIVE LOGITS
     efficiency
    0.07
    功能性
    0.07
     capabilities
    0.07
    𝑖
    0.07
    𝘱
    0.06
    工作作风
    0.06
    效率
    0.06
    _LINK
    0.06
     tid
    0.06
     capability
    0.06
    Act Density 0.014%

    No Known Activations