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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mass
    -0.07
    蓝
    -0.07
     worsh
    -0.06
    Vict
    -0.06
     Mass
    -0.06
     Ralph
    -0.06
    \Id
    -0.06
    ยนแปลง
    -0.06
    妮
    -0.06
     stocked
    -0.06
    POSITIVE LOGITS
    (files
    0.07
     Showing
    0.07
    Renderer
    0.07
    せる
    0.07
     apiUrl
    0.07
    rat
    0.07
    "profile
    0.07
     kami
    0.07
    »,
    0.07
     Charleston
    0.07
    Act Density 0.000%

    No Known Activations