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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ➲
    -0.07
    ulner
    -0.07
    便捷
    -0.07
    [rand
    -0.07
    大奖
    -0.06
    袭击
    -0.06
    RV
    -0.06
    险
    -0.06
    liable
    -0.06
    而已
    -0.06
    POSITIVE LOGITS
    ModelCreating
    0.07
     "");↵
    0.07
     Dominic
    0.07
    ゟ
    0.07
    뽈
    0.07
     coke
    0.06
    _CONTROL
    0.06
    mtree
    0.06
     XCTAssertEqual
    0.06
     OUT
    0.06
    Act Density 0.009%

    No Known Activations