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

    Neuronpedia

    INDEX
    Explanations

    Non-English fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𐤏
    -0.07
    茴
    -0.07
    ဿ
    -0.07
    ẩu
    -0.07
     stripes
    -0.06
    뱐
    -0.06
    'S
    -0.06
     mystery
    -0.06
    -League
    -0.06
    馝
    -0.06
    POSITIVE LOGITS
    مب
    0.08
     Connector
    0.07
     nueva
    0.07
    Gui
    0.07
    /__
    0.07
    所
    0.07
     Debug
    0.07
    ネタ
    0.07
    .items
    0.07
    ……
    0.07
    Act Density 0.126%

    No Known Activations