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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NT
    -0.07
    реди
    -0.07
     planner
    -0.06
    gulp
    -0.06
     Imperial
    -0.06
     rolling
    -0.06
     Rolling
    -0.06
     lp
    -0.06
     Printing
    -0.06
     Boeh
    -0.06
    POSITIVE LOGITS
    db
    0.06
    kem
    0.06
     dispensaries
    0.06
    вещ
    0.06
     студ
    0.06
    clamation
    0.06
     pregunta
    0.06
    (lat
    0.06
     spont
    0.06
     Vert
    0.06
    Act Density 0.030%

    No Known Activations