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
     ASD
    -0.07
     gbc
    -0.07
     impl
    -0.07
    _thresh
    -0.07
    di
    -0.06
    𝜙
    -0.06
    izi
    -0.06
    全国人大
    -0.06
    ;\
    -0.06
     ν
    -0.06
    POSITIVE LOGITS
    闰
    0.08
    阆
    0.07
    <TKey
    0.07
    桦
    0.07
     إعادة
    0.07
    [color
    0.07
    攽
    0.07
     עבודת
    0.06
    ITIONAL
    0.06
    条约
    0.06
    Act Density 0.012%

    No Known Activations