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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    到底
    -0.07
    nz
    -0.06
    lfw
    -0.06
    ERICA
    -0.06
    \Helper
    -0.06
    tron
    -0.06
    \Blueprint
    -0.06
    links
    -0.06
    ToFile
    -0.06
    CppCodeGenWriteBarrier
    -0.06
    POSITIVE LOGITS
    Db
    0.07
     preg
    0.07
     دور
    0.06
     Lib
    0.06
     hats
    0.06
     dab
    0.06
     ax
    0.06
     marsh
    0.06
    (Form
    0.06
     система
    0.06
    Act Density 0.028%

    No Known Activations