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

    Neuronpedia

    INDEX
    Explanations

    Windows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    training
    -0.07
     Australia
    -0.07
    넠
    -0.06
    晙
    -0.06
     pageNo
    -0.06
    ≾
    -0.06
    摹
    -0.06
    ⍩
    -0.06
    ↫
    -0.06
    ureen
    -0.06
    POSITIVE LOGITS
     MODULE
    0.07
    医用
    0.07
    Objects
    0.07
    _H
    0.07
     lệnh
    0.07
    patches
    0.07
    UILDER
    0.06
     underground
    0.06
     parses
    0.06
     QUI
    0.06
    Act Density 0.009%

    No Known Activations