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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чаются
    -0.06
     Cupertino
    -0.06
    Legacy
    -0.06
    Backend
    -0.06
     LOCATION
    -0.06
     Sheets
    -0.06
    .mount
    -0.06
    ़
    -0.06
    挑
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    شب
    0.07
     <<
    0.07
    RIA
    0.07
     Allied
    0.06
    anteed
    0.06
    ์ต
    0.06
    “↵↵
    0.06
    şk
    0.06
    films
    0.06
    处理
    0.06
    Act Density 0.000%

    No Known Activations