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

    Neuronpedia

    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oth
    -0.07
    IMITIVE
    -0.06
    �始
    -0.06
    irc
    -0.06
    forced
    -0.06
     Dollars
    -0.06
    LOOD
    -0.06
    від
    -0.06
     Commands
    -0.06
     zdarma
    -0.06
    POSITIVE LOGITS
     öğ
    0.06
     法
    0.06
     flux
    0.06
     baseURL
    0.06
     Lua
    0.06
    Mel
    0.06
    Highlighted
    0.06
     osg
    0.06
    KER
    0.05
     composers
    0.05
    Act Density 0.005%

    No Known Activations