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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     non
    -0.07
    "),
    -0.07
    ")
    -0.07
    '],
    -0.07
     detects
    -0.06
     translated
    -0.06
    (strlen
    -0.06
     Davidson
    -0.06
     Finals
    -0.06
     leverage
    -0.06
    POSITIVE LOGITS
    /use
    0.07
    ельно
    0.07
     розта
    0.06
    WillDisappear
    0.06
    邊
    0.06
    ắc
    0.06
    amily
    0.06
     viewWillAppear
    0.06
    -Pack
    0.06
    SO
    0.06
    Act Density 0.057%

    No Known Activations