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

    Neuronpedia

    INDEX
    Explanations

    methods and techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModelIndex
    -0.07
    (builder
    -0.06
    hor
    -0.06
    (Html
    -0.06
     максим
    -0.06
     아니
    -0.06
    ("")]↵
    -0.06
    urrent
    -0.06
    unks
    -0.06
     ------
    -0.06
    POSITIVE LOGITS
     popul
    0.06
     ฉ
    0.06
     acad
    0.06
    ít
    0.06
    ังจาก
    0.06
    Added
    0.06
     Chad
    0.06
    增
    0.06
     bespoke
    0.06
     hydr
    0.06
    Act Density 0.050%

    No Known Activations