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

    Neuronpedia

    INDEX
    Explanations

    Code/Configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jewel
    -0.08
     steal
    -0.07
    شاء
    -0.07
     Bruins
    -0.06
    SceneManager
    -0.06
     Nath
    -0.06
    omap
    -0.06
     мира
    -0.06
    agh
    -0.06
     Menu
    -0.06
    POSITIVE LOGITS
    =sc
    0.07
     بیشتر
    0.07
     більш
    0.06
     irc
    0.06
    sty
    0.06
     abdom
    0.06
     großen
    0.06
    .dtp
    0.06
    �
    0.06
    १९
    0.06
    Act Density 0.046%

    No Known Activations