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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fakt
    -0.07
     findViewById
    -0.06
     nf
    -0.06
     ami
    -0.06
    (List
    -0.06
    Angle
    -0.06
    反感
    -0.06
     across
    -0.06
    -angle
    -0.06
    athering
    -0.06
    POSITIVE LOGITS
    控制系统
    0.07
     connectionString
    0.07
    设计方案
    0.07
    党组
    0.07
    命周期
    0.07
    /proto
    0.07
     risky
    0.07
     코드
    0.07
    ｋ
    0.06
    .Startup
    0.06
    Act Density 0.016%

    No Known Activations