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

    Neuronpedia

    INDEX
    Explanations

    Solar neutrinos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (gen
    -0.07
     recursion
    -0.07
    UnitOfWork
    -0.07
     집
    -0.07
     drew
    -0.07
    +=
    -0.06
     לר
    -0.06
    \Php
    -0.06
    На
    -0.06
    面试
    -0.06
    POSITIVE LOGITS
    enerator
    0.08
     franca
    0.08
    佴
    0.07
    (layout
    0.07
    agma
    0.07
     гор
    0.07
    دي
    0.06
    GRAY
    0.06
    🔓
    0.06
     SHORT
    0.06
    Act Density 0.013%

    No Known Activations