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

    Neuronpedia

    INDEX
    Explanations

    Action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เมษายน
    -0.08
    sanız
    -0.07
     throm
    -0.07
     Consortium
    -0.07
    协商
    -0.07
    ซ
    -0.07
    连夜
    -0.07
     sha
    -0.06
    遠
    -0.06
    备案
    -0.06
    POSITIVE LOGITS
    IELD
    0.09
    Compound
    0.09
    Bl
    0.08
    医疗机构
    0.07
    Construct
    0.07
    Credit
    0.07
    .contents
    0.07
    0.07
    bos
    0.07
    ICS
    0.07
    Act Density 0.001%

    No Known Activations