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

    Neuronpedia

    INDEX
    Explanations

    Race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    startup
    -0.07
     Startup
    -0.07
     привед
    -0.06
     pint
    -0.06
     mash
    -0.06
    олю
    -0.06
     숨
    -0.06
    NF
    -0.06
     왕
    -0.06
     shopper
    -0.06
    POSITIVE LOGITS
    _candidate
    0.07
    .el
    0.07
    .preventDefault
    0.07
     startled
    0.06
    elix
    0.06
     forgetting
    0.06
    ForObject
    0.06
    finally
    0.06
    .isArray
    0.06
     moot
    0.06
    Act Density 0.028%

    No Known Activations