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

    Neuronpedia

    INDEX
    Explanations

    career appointments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hukuk
    -0.06
    explicit
    -0.06
    ﻨ
    -0.06
     Barbie
    -0.06
     XII
    -0.06
    Intensity
    -0.06
     EI
    -0.06
    .inject
    -0.06
     CLIIIK
    -0.06
     Wave
    -0.06
    POSITIVE LOGITS
    cos
    0.07
    _dr
    0.07
     sells
    0.07
     pole
    0.06
    Lists
    0.06
    -ne
    0.06
    Neighbor
    0.06
    狐
    0.06
    ipeline
    0.06
     MemoryStream
    0.06
    Act Density 0.030%

    No Known Activations