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

    Neuronpedia

    INDEX
    Explanations

    Membranes and filtration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     willingness
    -0.08
    祖国
    -0.07
    体育彩票
    -0.07
     lr
    -0.07
     Clement
    -0.07
    抵御
    -0.07
    Fal
    -0.07
     favourable
    -0.07
     criticisms
    -0.06
     Spanish
    -0.06
    POSITIVE LOGITS
    ject
    0.08
    _no
    0.07
    _taken
    0.07
    岘
    0.07
     SWITCH
    0.06
    slot
    0.06
    _convert
    0.06
     binary
    0.06
    潔
    0.06
    .mutex
    0.06
    Act Density 0.015%

    No Known Activations