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

    Neuronpedia

    INDEX
    Explanations

    military ranks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imagem
    -0.06
     Ara
    -0.06
     nuru
    -0.06
    _PRIVATE
    -0.06
    Friday
    -0.06
     ピ
    -0.06
    atrigesimal
    -0.06
     premium
    -0.06
     Betty
    -0.06
    V
    -0.06
    POSITIVE LOGITS
     wizard
    0.06
    �
    0.06
     Arab
    0.06
    총
    0.06
     metabolic
    0.06
    ersonic
    0.06
    бав
    0.06
    leader
    0.06
    getLast
    0.06
    foreign
    0.06
    Act Density 0.012%

    No Known Activations