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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etch
    -0.07
    eous
    -0.07
     berlin
    -0.06
     остав
    -0.06
     Tradition
    -0.06
    ordes
    -0.06
    positor
    -0.06
     ToDo
    -0.06
     спад
    -0.06
     potassium
    -0.06
    POSITIVE LOGITS
     Romanian
    0.08
    >"
    0.07
     dimension
    0.07
     wished
    0.07
     gemacht
    0.06
    remium
    0.06
    Serialize
    0.06
    (HttpContext
    0.06
    uart
    0.06
     [["
    0.06
    Act Density 0.010%

    No Known Activations