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
    קהילה
    -0.08
    �
    -0.07
     mechanic
    -0.07
    噪音
    -0.07
    钺
    -0.07
     kne
    -0.07
    payments
    -0.07
     Years
    -0.07
    uyến
    -0.07
    垠
    -0.07
    POSITIVE LOGITS
    onitor
    0.07
    著作
    0.07
     בספר
    0.07
    对策
    0.07
    ITOR
    0.06
    妙
    0.06
    寻找
    0.06
    Extractor
    0.06
     ephem
    0.06
    ajes
    0.06
    Act Density 0.012%

    No Known Activations