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

    Neuronpedia

    INDEX
    Explanations

    code functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Architect
    -0.08
     Cambridge
    -0.08
     textbooks
    -0.08
     adipisicing
    -0.07
    опр
    -0.07
    Institute
    -0.07
    @Spring
    -0.07
    Battle
    -0.07
     deserts
    -0.07
    Marshall
    -0.07
    POSITIVE LOGITS
     LUA
    0.11
     scripting
    0.10
     script
    0.10
     Lua
    0.10
     SCRIPT
    0.10
    Lua
    0.10
    _SCRIPT
    0.09
    -script
    0.09
     Script
    0.09
    script
    0.09
    Act Density 0.016%

    No Known Activations