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

    Neuronpedia

    INDEX
    Explanations

    neutral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bağır
    -0.07
     prolonged
    -0.07
     Vive
    -0.07
     cuối
    -0.07
     embark
    -0.07
     fy
    -0.07
     три
    -0.07
     smlouvy
    -0.06
    Cadastro
    -0.06
     oste
    -0.06
    POSITIVE LOGITS
     neutral
    0.10
    Neutral
    0.09
     Neutral
    0.08
     Rebel
    0.07
    BOT
    0.07
     Activ
    0.07
    dration
    0.06
    dealer
    0.06
     metals
    0.06
    atest
    0.06
    Act Density 0.006%

    No Known Activations