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

    Neuronpedia

    INDEX
    Explanations

    him

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depression
    -0.07
     Pentagon
    -0.07
    模型
    -0.07
     bolts
    -0.07
    ío
    -0.06
     ray
    -0.06
     toxins
    -0.06
    ataset
    -0.06
     Assessment
    -0.06
     ber
    -0.06
    POSITIVE LOGITS
    Rotate
    0.06
    etrain
    0.06
    \Db
    0.06
    (mc
    0.06
    _URI
    0.05
    ازات
    0.05
    وین
    0.05
    543
    0.05
     hydr
    0.05
    股票
    0.05
    Act Density 0.020%

    No Known Activations