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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PLIED
    -0.07
     DELETE
    -0.07
    CELL
    -0.07
    جيل
    -0.07
    executor
    -0.07
    ень
    -0.07
     Levine
    -0.07
    ér
    -0.07
    kins
    -0.07
    划分
    -0.06
    POSITIVE LOGITS
     세계
    0.08
     OkHttpClient
    0.07
     służ
    0.07
    荷兰
    0.07
     fault
    0.07
    跟踪
    0.07
    蜚
    0.07
    -client
    0.07
     Rohingya
    0.06
     halk
    0.06
    Act Density 0.016%

    No Known Activations