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
     novels
    -0.08
    ulu
    -0.07
     Review
    -0.07
     Michel
    -0.07
     UV
    -0.07
    _Show
    -0.07
    eksiyon
    -0.07
    ов
    -0.06
     Uk
    -0.06
     novel
    -0.06
    POSITIVE LOGITS
    teri
    0.07
    弋
    0.07
     Agr
    0.07
    こちら
    0.07
    members
    0.07
    บรร
    0.07
     Gary
    0.07
     Bên
    0.07
     Jason
    0.07
     jasmine
    0.07
    Act Density 0.024%

    No Known Activations