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

    Neuronpedia

    INDEX
    Explanations

    compiling code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tenant
    -0.08
     Data
    -0.07
     necessitat
    -0.07
     Outfit
    -0.07
    _VALUES
    -0.07
    -All
    -0.07
     parentheses
    -0.07
    改革
    -0.07
     Academic
    -0.07
     paris
    -0.07
    POSITIVE LOGITS
    Executable
    0.11
     binaries
    0.10
     executable
    0.10
     produzido
    0.10
     النهائي
    0.10
    生成
    0.09
     produzir
    0.09
     runnable
    0.09
    Produced
    0.09
     masterpiece
    0.09
    Act Density 0.006%

    No Known Activations