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

    Neuronpedia

    INDEX
    Explanations

    coding special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SOC
    -0.07
    _HPP
    -0.07
     Healing
    -0.07
     tents
    -0.07
    (**
    -0.07
    Mirror
    -0.07
     Burb
    -0.07
     Wesley
    -0.06
     Scientists
    -0.06
     interrog
    -0.06
    POSITIVE LOGITS
    .Per
    0.06
    яют
    0.06
    лок
    0.06
    ٌ
    0.06
    -basic
    0.06
    _numpy
    0.06
     QMainWindow
    0.06
     gover
    0.05
    اسیون
    0.05
    ousel
    0.05
    Act Density 0.065%

    No Known Activations