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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .prot
    -0.07
    쿨
    -0.07
    打扫
    -0.07
    .ToolTip
    -0.07
    苫
    -0.07
    \Entities
    -0.07
     PU
    -0.07
     convolution
    -0.07
    �
    -0.07
     Berger
    -0.07
    POSITIVE LOGITS
    둁
    0.07
     Все
    0.07
     Researchers
    0.07
    อาท
    0.07
    ﴫ
    0.07
    詩
    0.07
    '];
↵
    0.07
     military
    0.07
    EXAMPLE
    0.06
    Investigators
    0.06
    Act Density 0.001%

    No Known Activations