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

    Neuronpedia

    INDEX
    Explanations

    mathematical and scientific computing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DV
    -0.07
     Tamb
    -0.07
    ngthen
    -0.07
    quine
    -0.07
     Hispanics
    -0.06
     древ
    -0.06
    ácil
    -0.06
    Fortunately
    -0.06
     glac
    -0.06
     dansk
    -0.06
    POSITIVE LOGITS
    abe
    0.07
    热搜
    0.07
    RO
    0.07
    	On
    0.07
    上限
    0.07
    ורה
    0.07
    ่ง
    0.07
    _AdjustorThunk
    0.07
    Polygon
    0.07
    SerializeField
    0.07
    Act Density 0.038%

    No Known Activations