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

    Neuronpedia

    INDEX
    Explanations

    code modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SKTOP
    -0.07
    (round
    -0.07
    新型
    -0.07
    办公厅
    -0.06
    Toolkit
    -0.06
     khuyến
    -0.06
    电商
    -0.06
    的确
    -0.06
    ]^
    -0.06
    .contrib
    -0.06
    POSITIVE LOGITS
    ぺ
    0.07
    _SEGMENT
    0.07
     summer
    0.06
    想去
    0.06
    Wind
    0.06
     dissip
    0.06
    .getDay
    0.06
     plastics
    0.06
    伯
    0.06
     deception
    0.06
    Act Density 0.107%

    No Known Activations