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
    patients
    -0.07
    시는
    -0.06
     FD
    -0.06
    她
    -0.06
     spoiler
    -0.06
     /\
    -0.06
     leer
    -0.06
     Neg
    -0.06
    -bar
    -0.06
    _publish
    -0.06
    POSITIVE LOGITS
     OMAP
    0.07
    訳
    0.07
     FullName
    0.06
    ancybox
    0.06
    .fullName
    0.06
    GE
    0.06
    
    0.06
     Inject
    0.06
     invasion
    0.06
    ΑΝΤ
    0.06
    Act Density 0.005%

    No Known Activations