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

    Neuronpedia

    INDEX
    Explanations

    portuguese and code mix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ie
    -0.08
     delimiter
    -0.07
     Protocol
    -0.06
     breeds
    -0.06
     dataList
    -0.06
     rider
    -0.06
     вел
    -0.06
     bean
    -0.06
     Locker
    -0.06
     digit
    -0.06
    POSITIVE LOGITS
    'aff
    0.08
    ンディ
    0.07
    -west
    0.06
     киш
    0.06
    arged
    0.06
    endid
    0.06
    nia
    0.06
    обще
    0.06
     payday
    0.06
    _WAIT
    0.06
    Act Density 0.102%

    No Known Activations