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

    Neuronpedia

    INDEX
    Explanations

    whitening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Script
    -0.07
    agt
    -0.06
    .getContentPane
    -0.06
    φέρει
    -0.06
    rotein
    -0.06
    Utility
    -0.06
    _nullable
    -0.06
     ALT
    -0.06
    LU
    -0.06
    _am
    -0.06
    POSITIVE LOGITS
    en
    0.09
     эконом
    0.07
    人
    0.07
     indemn
    0.07
     ๆ
    0.07
     现
    0.07
    =wx
    0.07
    Video
    0.06
    EN
    0.06
    aching
    0.06
    Act Density 0.003%

    No Known Activations