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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combustion
    -0.07
    ，其中
    -0.06
    ACT
    -0.06
    项目
    -0.06
    Indented
    -0.06
    egov
    -0.06
    SetActive
    -0.06
    loading
    -0.06
     ranks
    -0.06
     ubuntu
    -0.06
    POSITIVE LOGITS
    /libs
    0.06
     slov
    0.06
    어요
    0.06
     şun
    0.06
    �
    0.06
     sedm
    0.06
     LOL
    0.06
     мор
    0.06
     бел
    0.06
    ης
    0.06
    Act Density 0.003%

    No Known Activations