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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jarvis
    -0.07
     dosy
    -0.07
    deck
    -0.07
     defence
    -0.07
    počet
    -0.07
     traders
    -0.07
    ourse
    -0.07
     Royale
    -0.06
    DEN
    -0.06
    셜
    -0.06
    POSITIVE LOGITS
    Guess
    0.07
    /dev
    0.07
    :'',
    0.06
     Перед
    0.06
     mw
    0.06
    engu
    0.06
    iteDatabase
    0.06
    �
    0.06
    γα
    0.06
    .ForEach
    0.06
    Act Density 0.040%

    No Known Activations