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
    ้แก
    -0.07
     pha
    -0.06
     COM
    -0.06
     světa
    -0.06
    zung
    -0.06
    Ki
    -0.06
    铁
    -0.06
     corridor
    -0.06
     pracy
    -0.06
    undaki
    -0.06
    POSITIVE LOGITS
    дах
    0.08
    assert
    0.07
    ")).
    0.07
    uchsia
    0.07
    ').
    0.07
     mostly
    0.06
    sections
    0.06
    リスト
    0.06
    )").
    0.06
    /watch
    0.06
    Act Density 0.007%

    No Known Activations