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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Electron
    -0.07
    arius
    -0.07
    可以看到
    -0.07
    Finder
    -0.07
    PointerException
    -0.07
     retention
    -0.07
     communication
    -0.07
     behavioral
    -0.07
    深知
    -0.07
    analytics
    -0.06
    POSITIVE LOGITS
    两侧
    0.07
    emade
    0.07
    几率
    0.07
     kl
    0.07
     tyr
    0.07
    -Nov
    0.07
    ミニ
    0.06
    fas
    0.06
    _projects
    0.06
    TypeId
    0.06
    Act Density 0.007%

    No Known Activations