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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domest
    -0.07
     freund
    -0.07
     Gareth
    -0.07
    菏
    -0.07
     Stem
    -0.06
    reduce
    -0.06
     atas
    -0.06
    ī
    -0.06
    须
    -0.06
    weed
    -0.06
    POSITIVE LOGITS
    잖아요
    0.07
     JSBracketAccess
    0.06
    Genres
    0.06
    够
    0.06
    üc
    0.06
    however
    0.06
    icont
    0.06
    BOT
    0.06
    IsValid
    0.06
    局面
    0.06
    Act Density 0.212%

    No Known Activations