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

    Neuronpedia

    INDEX
    Explanations

    Science fields

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     이렇게
    -0.07
    minate
    -0.07
    了不少
    -0.07
    Executive
    -0.07
    ド
    -0.07
    /P
    -0.07
    _Offset
    -0.07
     toughest
    -0.07
    Seven
    -0.06
    下来的
    -0.06
    POSITIVE LOGITS
    -scal
    0.08
    _ros
    0.07
     aware
    0.07
     dbHelper
    0.07
     keras
    0.07
    Islam
    0.07
    finance
    0.07
     literacy
    0.07
    raq
    0.07
     Physics
    0.07
    Act Density 0.131%

    No Known Activations